{ "checkpoint_id": "miles-qwen3.8-27b-06448b429f21/run-06448b429f21/training/eval-snapshots/step_99", "job_id": "q08d01w", "output_files": { "LICENSE": { "bytes": 11544, "sha256": "bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a" }, "README.md": { "bytes": 5420, "sha256": "5acdea1e59271c4ef7d388670e5bd8860763523f23fb8a74246a25fecd0d415b" }, "chat_template.jinja": { "bytes": 8952, "sha256": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041" }, "config.json": { "bytes": 4312, "sha256": "191e0af232104ed8b65258cf3fb2b842e288008baca7633c11b82a1ac7203aab" }, "crc32.txt": { "bytes": 238, "sha256": "b42dd291f5f98b05807e458f5b47849969a9b3326acbf0c97d28b05826740b83" }, "expert-provenance.json": { "bytes": 5482, "sha256": "4574789080230c074bcf1a3b6fd9eb70fb00d816677e7bb2e4afabb3b6a8919a" }, "generation_config.json": { "bytes": 202, "sha256": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e" }, "merges.txt": { "bytes": 3353259, "sha256": "a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d" }, "model-00001-of-00018.safetensors": { "bytes": 3045232952, "sha256": "5dc57b22e93ebb1983407023af1f8a320e71ff58f8555e7c91eaaa6787a4ca59" }, "model-00002-of-00018.safetensors": { "bytes": 3043080488, "sha256": "dbb7cfffb2ec45db6f322311a6478d0785db4818b4ac0346f2f608843dca2cb5" }, "model-00003-of-00018.safetensors": { "bytes": 2542796928, "sha256": "64a59a867e7414771971137481b71deabab8e4f361b7f22dd3a6e5f9c2717b4f" }, "model-00004-of-00018.safetensors": { "bytes": 3988973496, "sha256": "6544a49e77c95c7efd3fd09095634e6edd76f69f3f32820f356507bb4486d699" }, "model-00005-of-00018.safetensors": { "bytes": 2099340032, "sha256": "ddb724ca400d4d92d614c63da42fdc0aa0d5b7223670d530fa85c4ff59f856ad" }, "model-00006-of-00018.safetensors": { "bytes": 3979554136, "sha256": "95fda08b98d0992100a60d8a3d14a0d6c740407ee6f2fdc03c79b2fe03ecea2f" }, "model-00007-of-00018.safetensors": { "bytes": 2108759408, "sha256": "7a6d3b460022bf3b6b0e8df9033aac2cae84de142306f65a44b8bdcee7865d17" }, "model-00008-of-00018.safetensors": { "bytes": 3979554136, "sha256": "5cec2cf589e57fef9f9cbb3df9af4d4468b58304d9238c686f71a6a81418d919" }, "model-00009-of-00018.safetensors": { "bytes": 2108759408, "sha256": "b47a112b7e024943167d72d6da104c7bc8617e7b78dde360c8578368a8679ec5" }, "model-00010-of-00018.safetensors": { "bytes": 3979554136, "sha256": "202749a3f61f9f8e8893c58f4d7052a8c165d0a07ba56928edc87b48344e83da" }, "model-00011-of-00018.safetensors": { "bytes": 2108759408, "sha256": "6f5c889bbe7cdd98620257fdd4d74bd8c2c644c793ef565bf648a43e6367a178" }, "model-00012-of-00018.safetensors": { "bytes": 3979554136, "sha256": "c99974af17d47aaa1f096d74fa4ceb1ebab0f30fcc4df11b2db1edf87fcd1668" }, "model-00013-of-00018.safetensors": { "bytes": 2108759408, "sha256": "0f621a75043527dced82ec209b09312f42ed5ec25b7a1eee4442f69120e065d1" }, "model-00014-of-00018.safetensors": { "bytes": 3979554136, "sha256": "dc238ff43e8787d6072907bdad95eac369ef0eed55bc9d826d8218ed7ea4d175" }, "model-00015-of-00018.safetensors": { "bytes": 2108759408, "sha256": "3e07c7be92a7284db6c2635dbddffc98c125aa797627d985083808c3aea43a27" }, "model-00016-of-00018.safetensors": { "bytes": 3979564472, "sha256": "6e499a617e78aec049c5859f091c10e16d4e3cf1190df8ac3ce9c02c16ecca50" }, "model-00017-of-00018.safetensors": { "bytes": 2108759408, "sha256": "e176bf3cdf4d62cd960662b91a594cf326c0ae5ceca4037657f1ba8a5117b2ae" }, "model-00018-of-00018.safetensors": { "bytes": 2542796896, "sha256": "2af195e3e76d5ab5bcf0e3e35a81c64899de5293f0efb7fd572d461b6422b509" }, "model.safetensors.index.json": { "bytes": 83872, "sha256": "06ef64c782c1a5190e803dbf59abaab979f95992edf079dc9c708ec653d8a12f" }, "preprocessor_config.json": { "bytes": 390, "sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516" }, "tokenizer.json": { "bytes": 12809320, "sha256": "0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3" }, "tokenizer_config.json": { "bytes": 17928, "sha256": "b11349aafa7cdc6a320767cf7ceb29ed82f7eda5d65e8e0819e76f0ce947bf27" }, "video_preprocessor_config.json": { "bytes": 385, "sha256": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13" }, "vocab.json": { "bytes": 6722759, "sha256": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003" } }, "output_shards": 18, "prepared_at": "2026-10-22T06:55:58.288709+00:00", "repo_id": "baseten/caesar-cipher-adam-qwen38_27b-expert", "run_id": "final-trained-experts-18shards-20261022", "schema": "reasoning-gym-cloud-export-v1", "source_checkpoint_bytes": 53815103533, "source_files": { "chat_template.jinja": { "bytes": 8952, "sha256": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041" }, "config.json": { "bytes": 4312, "sha256": "191e0af232104ed8b65258cf3fb2b842e288008baca7633c11b82a1ac7203aab" }, "crc32.txt": { "bytes": 238, "sha256": "b42dd291f5f98b05807e458f5b47849969a9b3326acbf0c97d28b05826740b83" }, "generation_config.json": { "bytes": 202, "sha256": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e" }, "merges.txt": { "bytes": 3353259, "sha256": "a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d" }, "model-00001.safetensors": { "bytes": 535871064, "sha256": "3904ed70e9e15af386f8b01ea448ea1b5f8291497bcb818414c8b0728c0da903" }, "model-00002.safetensors": { "bytes": 230697888, "sha256": "ea0316ce83338ccbd17a8ab2ae2d07c0498df0f22353e19763341d7edb53e4f3" }, "model-00003.safetensors": { "bytes": 535850344, "sha256": "fc26643fe59558198f72d0402b9d834097a830fb246b63bd5f75ec086ceb6943" }, "model-00004.safetensors": { "bytes": 230697888, "sha256": "b31078eae03c89586207bb778c1f72045251c46ed6b34e3fd9723b125b3b829d" }, "model-00005.safetensors": { "bytes": 535850352, "sha256": "29940a8e9386d063a768480a9a23b857476175dfef912ef5d2c07fe358868dc8" }, "model-00006.safetensors": { "bytes": 230697888, "sha256": "2b5c0d96dd35b5414685a18ea8f4635bc562747c28d1470fcf5fbe6adb4ce069" }, "model-00007.safetensors": { "bytes": 534774784, "sha256": "1b21a9f59cef52063ec6738b43847afa873183dfdc42140bec1191cc0d6295ca" }, "model-00008.safetensors": { "bytes": 209737088, "sha256": "bcaa516055f8dea95dc29cce15ed4d8341136704be2ee3a4cfb8b3727b34bcb3" }, "model-00009.safetensors": { "bytes": 535850352, "sha256": "0b8b2ae7274a2ecd5a5b250db159d94c00109b91acba85cffccb3b1f0fe75857" }, "model-00010.safetensors": { "bytes": 230697888, "sha256": "be73c99f57a93d5fa8cbc1c6fa7dc95b2597bc2c34244623459212e0b3561399" }, "model-00011.safetensors": { "bytes": 535850352, "sha256": "f563bc776dd0223899f62157716d1ee2b62d4594b60e475af9228ea8d106ee14" }, "model-00012.safetensors": { "bytes": 230697888, "sha256": "adcf75b801cee5abdf1f46426e459560f2184145868d8e59e97e0af6abcfc95e" }, "model-00013.safetensors": { "bytes": 535850352, "sha256": "8a4ce6adc245ef84005d0f3fa555fdfe8c457988a87c258f9edd43c88e185f46" }, "model-00014.safetensors": { "bytes": 230697888, "sha256": "9dbd7fa21adf268be480d6545915f3772dda6d5eb12042ea9fd064ea22be432c" }, "model-00015.safetensors": { "bytes": 534774784, "sha256": "9fb0c1cf6b1540582e7a54421317d3f5e2486677d7a03cf3f79329490e7b7fb2" }, "model-00016.safetensors": { "bytes": 209737088, "sha256": "3930a95b0a5f289eab6f4c9792faa8e160c38778e9c0666f2cf0b006c8fa7cc9" }, "model-00017.safetensors": { "bytes": 535850352, "sha256": "8ef92e799951b6e4c2c0085f20445e8521c75ea085e68d585c2068db7d5191b1" }, "model-00018.safetensors": { "bytes": 230697888, "sha256": "288a5280cd0500b269c5da11b894416e997650ff72ac1916958dd84d24cb5e71" }, "model-00019.safetensors": { "bytes": 535850352, "sha256": "7aa1882c96f7b7b0a7c08d2443b4930b757decea5fa9bd0c18e9c9f4beacf79b" }, "model-00020.safetensors": { "bytes": 230697888, "sha256": "278d64046db694c98ea7c032ceccb933e7a4bd548bb6a90d62610f58de9fd273" }, "model-00021.safetensors": { "bytes": 535850352, "sha256": "7038f7263dea35ddbecfbb1f3ed510109cf0219f639a6ebe40d93f1466f89f39" }, "model-00022.safetensors": { "bytes": 230697888, "sha256": "77afc0e8e7ea0203084f9c317f404b69758e91b2d8969905f98b799d00eb78fb" }, "model-00023.safetensors": { "bytes": 534774784, "sha256": "8018eb5855a3cb70809814ddcd7165c75ec289e452da2d8879a8786e0036c610" }, "model-00024.safetensors": { "bytes": 209737088, "sha256": "0f064a7ec6efbd905ed8ac8953751e694e42056b203c4821ba56fea02ccc4b72" }, "model-00025.safetensors": { "bytes": 535850344, "sha256": "a255bc83451552be348775a43bc89e01fe8e8b7345a4e739ed8ef8c0cd479840" }, "model-00026.safetensors": { "bytes": 230697888, "sha256": "0bbad42b07a11b690dee2004ba14581377a52139e4e75fe081b88e161ae3de5c" }, "model-00027.safetensors": { "bytes": 535850352, "sha256": "56359943f3e9dfca3519c0bce3c8334358213d8acb4fbc698a314c19062e80f5" }, "model-00028.safetensors": { "bytes": 230697888, "sha256": "6f1947bcbcf47e6bda1988a43e7a65b2fc16fba729bd35a577595e1dcd495163" }, "model-00029.safetensors": { "bytes": 535850352, "sha256": "0fc8d963af239d00a67dd7eb4fb9616c419a68a1a8d2a055f71ecf2bee9d055f" }, "model-00030.safetensors": { "bytes": 230697888, "sha256": "c6e880397a05ae0b1b5d79976cd3778a4024f9da9cc37414c20f6057e632c721" }, "model-00031.safetensors": { "bytes": 535850352, "sha256": "2954d5bb8f7563e322e18dbcfc01d92ec39200d92aac093971e68edab4f5e8dc" }, "model-00032.safetensors": { "bytes": 230697888, "sha256": "402b9bffd85b5ef40502c1e1a804de0d08458e5ba55bd1a3f112ae94e8ed829d" }, "model-00033.safetensors": { "bytes": 534774784, "sha256": "fe2bfaebc1dbd05f111b73bb714d9e1fe28e5bf0ce23f0b88e07baf62b4b0fa1" }, "model-00034.safetensors": { "bytes": 209737088, "sha256": "cb35029a5680c5c1c77349460c7c6688b43f3e127611733c355b7ffa09bb2897" }, "model-00035.safetensors": { "bytes": 535850352, "sha256": "f20e9e288ee831c0a28683e448c4b1fb8371dbe6a89153cfa389baadece5ac28" }, "model-00036.safetensors": { "bytes": 230697888, "sha256": "a1243ad01cef908632c2368545815cd7d703655d8b1118a748be6074891afcf6" }, "model-00037.safetensors": { "bytes": 535850352, "sha256": "d659250f0c783a274cbef84d24997778bf5b84d62eb85227f320715d4e0abea5" }, "model-00038.safetensors": { "bytes": 230697888, "sha256": "3325b0b8748cf3d49cf38f3f50d3820fbd51e358a3795ca9add703897523854e" }, "model-00039.safetensors": { "bytes": 535850352, "sha256": "7415cdd94f2be2d24740e669ba65a0e626ec453344b6d9c0b2931dc0f5819fe6" }, "model-00040.safetensors": { "bytes": 230697888, "sha256": "e8919b385ce70816bb7f1eb321c8d5b84d89b39fcdf5bca0b063e7ad21065045" }, "model-00041.safetensors": { "bytes": 534774784, "sha256": "5888f93080c6060dbf1d37ac3be41e9a4a2b43f2319b526170a13730d38b0f0b" }, "model-00042.safetensors": { "bytes": 209737088, "sha256": "1b7225dc37e7331615958fdf0905518ce0a1b2760d50c3c73bfa621c73e19e79" }, "model-00043.safetensors": { "bytes": 535850352, "sha256": "f5e29decc770041770f13fb444358677d98a8222fb8d6e1bf3e44db8253e4e25" }, "model-00044.safetensors": { "bytes": 230697888, "sha256": "0696fd6f685cd255d5bae0bb679ffb0831e07f7f94176edfcd2674eee3416f73" }, "model-00045.safetensors": { "bytes": 535850352, "sha256": "55b5920aefe074fc3fa73c2829dec75a579ae04bebb5abfbb8950017489d2e2d" }, "model-00046.safetensors": { "bytes": 230697888, "sha256": "c1b0ecbac80d0428a94f303376f1456222169ae84621f3be39baab833cd5649b" }, "model-00047.safetensors": { "bytes": 534774784, "sha256": "6a7f2b56b7cbac13c5447e3957aaaf2c1bb83c463d33d225b053c10c62bca959" }, "model-00048.safetensors": { "bytes": 209737088, "sha256": "c1db707f9193d2f91bad88d119904f113cd0c85674bb73b1939b499c501ec2bc" }, "model-00049.safetensors": { "bytes": 535850352, "sha256": "e2fcf64a222eb81609d27c772dc502ea69b9bb7bb62a37c176829f37d65d2786" }, "model-00050.safetensors": { "bytes": 230697888, "sha256": "bd3319471da2bf8e4348d481dbd609691b44c926ec06840223167046836f6597" }, "model-00051.safetensors": { "bytes": 534774784, "sha256": "2000f361d663d247e05edd3693b7ec634841dc587a4fd235ebb4820bfb69343f" }, "model-00052.safetensors": { "bytes": 209737088, "sha256": "505ea44ff03e618c7b6c0a88c1dfce0d45f937e5c5895f64a1468a300b002fff" }, "model-00053.safetensors": { "bytes": 535850352, "sha256": "8e866ff3d4b3168b6eef1f00ccaf4cddcf0682b290e2b30c78961d11c9622cdb" }, "model-00054.safetensors": { "bytes": 230697888, "sha256": "a89ed695782721d2914148bdbcff08171df245e020c2fdec13e5fb49d2dae0d1" }, "model-00055.safetensors": { "bytes": 535850352, "sha256": "361de4ae49acd26b719063d29e1af99d5650d9a1270976b4e4b0e3da4b303bc1" }, "model-00056.safetensors": { "bytes": 230697888, "sha256": "1c8cfec7676017960ca556c5328dfdcd3be32703a32cfa47244a619a91078c80" }, "model-00057.safetensors": { "bytes": 535850352, "sha256": "84b5d9721c9ce55948c0f869bb0d280561dc8d84e4e7c1df1cde451e63992b7d" }, "model-00058.safetensors": { "bytes": 230697888, "sha256": "5fbd3ab09c449e255b3880193161e1b21a46aebf9229221dd19ac0605c6bf46c" }, "model-00059.safetensors": { "bytes": 534774784, "sha256": "ebf1ef80e3b7d7f63a504097857523d3ce7c245f335960d5e1ce02c18e31fa37" }, "model-00060.safetensors": { "bytes": 209737088, "sha256": "6aa3cfc9b56184bcc868682f12a61d5677c8f4f6334899fa02e3d2d13ef3e2f4" }, "model-00061.safetensors": { "bytes": 535850352, "sha256": "7fbddaa3bb48d4ae3cefed584d71b96f4e63c2a322734a7714e4fde54aa5e27e" }, "model-00062.safetensors": { "bytes": 230697888, "sha256": "02e55d00ba6c9834678548d2d52bc97df68ddf675a260d7e3402968c2707380e" }, "model-00063.safetensors": { "bytes": 535850352, "sha256": "00674163bc792143c026fb9a514ebff4d8d9f871713bca6d3db6007265513186" }, "model-00064.safetensors": { "bytes": 230697888, "sha256": "7a670aa7c56bbaaa232b0af2efc8aa07e97495e612213ec4f00c7c9db6c98266" }, "model-00065.safetensors": { "bytes": 535850352, "sha256": "674bb7c004eddd8e089375b7d5b9a2ace49d87a8a15cc8b975d2f02b49a190f9" }, "model-00066.safetensors": { "bytes": 230697888, "sha256": "46199a64b26ac0a07c31726e3a87eed6f446d607fbc9788f57c1d21b7d59f679" }, "model-00067.safetensors": { "bytes": 534774784, "sha256": "37ec1ddf530845e59cea6a0f300aa3f56791e30a412411d5a40eb07740c12dae" }, "model-00068.safetensors": { "bytes": 209737088, "sha256": "b69fbdefaf0a498dfe2ec3814508dcddd28bb853656afd663727566c2b2d84ab" }, "model-00069.safetensors": { "bytes": 535850344, "sha256": "06b9b36d7dbc054e31a802e72cc909cbcca11dbb6f81d17746ce5e9fc7674103" }, "model-00070.safetensors": { "bytes": 230697888, "sha256": "a95a8791530a6c238462237bd8ff8e49c6c40c1ce90985fb1a1eb951f2eba29d" }, "model-00071.safetensors": { "bytes": 535850352, "sha256": "3a3ab7b6b78488a1a088f34a63feff55bd752f44944d8a739c2459b0d66131e2" }, "model-00072.safetensors": { "bytes": 230697888, "sha256": "92741f6680e23740a7b148a31800e659c1e463e85d4b76c8c5782d4e96df33d7" }, "model-00073.safetensors": { "bytes": 535850352, "sha256": "4ece9786bf6be1272ceecd16e26960b7a92d2a310b535dd506c41000ac116fbb" }, "model-00074.safetensors": { "bytes": 230697888, "sha256": "9c25b491d5f0c7a1addc23a85edd251c5270f54f84ad670622deca3a79c7f049" }, "model-00075.safetensors": { "bytes": 535850352, "sha256": "ac5baaffc56daaca162a55ba097e3f7cb894fedc005ff8eeee908b11bbe71373" }, "model-00076.safetensors": { "bytes": 230697888, "sha256": "f756361129294ae864fc2f93524485f707e5d48f9086cdea97cdb72add08d9bd" }, "model-00077.safetensors": { "bytes": 534774784, "sha256": "ff687d313627b63797b46eef49c435966abaa7ec3a6924d9082d4fc392310a27" }, "model-00078.safetensors": { "bytes": 209737088, "sha256": "f3d11693151194183a25ab666e8dbd95802bd686fa14d119d497e889ff445406" }, "model-00079.safetensors": { "bytes": 535850352, "sha256": "75461af6387e122710203386129c3adadbe26461269d0aa49a99c85f8a947c1c" }, "model-00080.safetensors": { "bytes": 230697888, "sha256": "4a70681693a519347cf8c93ef4e728eda36142387cc6a6fd37152dbb82c53d78" }, "model-00081.safetensors": { "bytes": 535850352, "sha256": "863fbd12dd4693e046512d632e8a12e4a9454f7bcf4653d14bf1abe7304f834b" }, "model-00082.safetensors": { "bytes": 230697888, "sha256": "4a3f43a4b2514fc7e3e3caf4216ca373775c676bc9d2ec4809a1ca375918ddf8" }, "model-00083.safetensors": { "bytes": 535850352, "sha256": "6b3b89ebbf3b3051b9de3d9be6285db9b8b1e8851493b66cefb1a7bbb11ad79e" }, "model-00084.safetensors": { "bytes": 230697888, "sha256": "3fd4bbb3bc6436cca80150de382797a085e6f0514fa3d09dac8040643ef62c64" }, "model-00085.safetensors": { "bytes": 534774784, "sha256": "1ba79444cfe1dd0f3a7ba0422fbefc232a32cfe0d1fa228554e526b9f6de0b26" }, "model-00086.safetensors": { "bytes": 209737088, "sha256": "39659516549cc4606ce35f90e8a64c917a8c6883ba6b73ef06b9ee67a6633f08" }, "model-00087.safetensors": { "bytes": 535850352, "sha256": "6c8df3249c55eeb28918c98a2029b596c1600f4b2fb531c3a5b7cba28cf5b8dc" }, "model-00088.safetensors": { "bytes": 230697888, "sha256": "20e3c538b125616c31a29983fbea2f89db557450451b01face25994c8574e7ba" }, "model-00089.safetensors": { "bytes": 535850352, "sha256": "05a74b005cb85c91f2eb2d84487b27d179100235d0b946e105ddae4c80cc7849" }, "model-00090.safetensors": { "bytes": 230697888, "sha256": "ddfd83920a84916ef524054c84309e853e5e843672fa933a50b16d269b77543f" }, "model-00091.safetensors": { "bytes": 535850344, "sha256": "8fb1aa3d714fe252eef1ef8994edf709af3a86dd72132badc6cb71e465ca8b56" }, "model-00092.safetensors": { "bytes": 230697888, "sha256": "33fe2c3dc2b5837ba9f531c79c3c9bdb34907766dccd56aef742ed7740e470db" }, "model-00093.safetensors": { "bytes": 535850352, "sha256": "f7ea41956691e3ca4913da1fd67e8f7883f153e5bbe4785604d3d099dfa877b4" }, "model-00094.safetensors": { "bytes": 230697888, "sha256": "2ae1c6c51e039c8fbdf95a1cef3c95ee1db01fc6bf35885d0b1ae22f1c05aee7" }, "model-00095.safetensors": { "bytes": 534774784, "sha256": "5ee9357d3cd76a1a91c49d8b3e89a16e53caa7bdc7a05ea0ced11938f6ecf456" }, "model-00096.safetensors": { "bytes": 209737088, "sha256": "6471bc6bfe6af0f0f9caf1d961544c428056d88a989d5747d56afa3fbc710da6" }, "model-00097.safetensors": { "bytes": 535850352, "sha256": "f21ec664dd26d9640f844880313f2dc59fe5adea9a87f5c68c4d1f1a8113fca1" }, "model-00098.safetensors": { "bytes": 230697888, "sha256": "9cac3fd40c5543da1c48344cf782030a5622b0a961ad2f779a75053cd5e80fe0" }, "model-00099.safetensors": { "bytes": 535850352, "sha256": "870e3911996c2afa2e039768ebbd10e5a96e4f47ffdc98449dae12b57b5cdb7b" }, "model-00100.safetensors": { "bytes": 230697888, "sha256": "886c0e246abdb8edb2381ec9fb447612b62076e459f2c3904e060015b6332c83" }, "model-00101.safetensors": { "bytes": 535850352, "sha256": "46be1a3775ec41f258649b6dbc027f0785bd9f275fb4ef4c4b0c90caf419efcd" }, "model-00102.safetensors": { "bytes": 230697888, "sha256": "1f2595777d0e31dba999aeaee059de3ceb61d8cb365c4d85c4922a1aaea1ffa0" }, "model-00103.safetensors": { "bytes": 534774784, "sha256": "09ac412a699d5fadeb939951840304f1e77894bb63aed0ab56a0731b16b6f4ce" }, "model-00104.safetensors": { "bytes": 209737088, "sha256": "4777706e98ee174bbdf357feff387750f765953d6bc6d3cc64d55ac9caa0dca3" }, "model-00105.safetensors": { "bytes": 535850352, "sha256": "99c268f7e7795600044307371ae5dc2f67b9946d09e0b3befc71581c9ee69a82" }, "model-00106.safetensors": { "bytes": 230697888, "sha256": "21954ef2f23b5658d76018be2712e11d200f6ec82ce88b7a7851f7c98c553d20" }, "model-00107.safetensors": { "bytes": 535850352, "sha256": "f06c04951aed39579d5b968da21f91475e104b6925b344ed01246b8ce48d60bc" }, "model-00108.safetensors": { "bytes": 230697888, "sha256": "3f494adc86a96abd8251521256320330c1373c44415c9379a49c982a36ccaaaa" }, "model-00109.safetensors": { "bytes": 535850352, "sha256": "6a726c113ea57cf804eea5bf5f0bd674ceaa5647ca9dfa3d687d021f673d22b8" }, "model-00110.safetensors": { "bytes": 230697888, "sha256": "0c6ae8af972fad64e61c10f7e988f8f9c962892ebe08e715a6a1af3f737ef892" }, "model-00111.safetensors": { "bytes": 534774784, "sha256": "977f89888ab9bc4d53bb372bdddd29d1ca4615d31412524da8f80f0dde221016" }, "model-00112.safetensors": { "bytes": 209737088, "sha256": "3921abf086dc34fd995756d58c9acd651f120c70d3490012fe9ce834dd891d28" }, "model-00113.safetensors": { "bytes": 535850344, "sha256": "01b3f910a431899262d56a4658042beeae216bd9834a40f1fdbc5c5d0dbca4b0" }, "model-00114.safetensors": { "bytes": 230697888, "sha256": "95eb70f53597af69f59fbea7d4ced5aaaa35c8da9fd8173e375f1f5d5faaf8fb" }, "model-00115.safetensors": { "bytes": 535850352, "sha256": "a326f36b7be5a2c380347591a9476cae409e69a41eaeeb97d64a25701ffa864a" }, "model-00116.safetensors": { "bytes": 230697888, "sha256": "c89a5866f1794d37da768a66e4b3ad9a10acb296dd9a842722e917426a15c4af" }, "model-00117.safetensors": { "bytes": 535850352, "sha256": "9e0029000e43b4be5cd6095e157a44291eccc18f7179732cda8208b7dd3ccc75" }, "model-00118.safetensors": { "bytes": 230697888, "sha256": "a48776552e946ca16e53d55447407e02e1d1ae6ca623eb7632c1aa1f72b04973" }, "model-00119.safetensors": { "bytes": 535850352, "sha256": "be586f3147c3b0a803b5564432d599f0778cac40210d70776ed2bb6fc35eb714" }, "model-00120.safetensors": { "bytes": 230697888, "sha256": "3b2166f7cc91b7c17e67f53c93c08d8d821daaac6b3bd501063707e3f00ee9cb" }, "model-00121.safetensors": { "bytes": 534774784, "sha256": "90bd2cb87dc62b5f54cdabcb61f5233519f8541cd954e23d2239f26904430521" }, "model-00122.safetensors": { "bytes": 209737088, "sha256": "5a6e367e44d24c9459825d4f6aee98d2cdb35ad20892fea3251dd77dc745c255" }, "model-00123.safetensors": { "bytes": 534774784, "sha256": "6ea8a43976564f8a0e72c8d4eab87a39cf51c7a585f2d97c2d13d0eda8fea975" }, "model-00124.safetensors": { "bytes": 209737088, "sha256": "bb245966a7ace523271dccc469474b1ef1af448fb66793943289714a4cbbcacf" }, "model-00125.safetensors": { "bytes": 535850344, "sha256": "28cb6e26d3c6bd3943d5c43e84fed104b248061cdfb3faf2cb4df6c6c7c48ad0" }, "model-00126.safetensors": { "bytes": 230697888, "sha256": "6175f8e99c49e6a84f18d79d632f57d5170c97a7060a71e38b48130438561be2" }, "model-00127.safetensors": { "bytes": 535850344, "sha256": "6841ef2e455f6cd97f3dc9c51fce3aa79f6b4e744e9bf08a0dad031106406ad9" }, "model-00128.safetensors": { "bytes": 230687512, "sha256": "621bd4241cd06cbb8cefb615f5be327a3c93cbb823d674f48277459dfda031cf" }, "model-00129.safetensors": { "bytes": 2542796928, "sha256": "64a59a867e7414771971137481b71deabab8e4f361b7f22dd3a6e5f9c2717b4f" }, "model-00130.safetensors": { "bytes": 2542796896, "sha256": "2af195e3e76d5ab5bcf0e3e35a81c64899de5293f0efb7fd572d461b6422b509" }, "model.safetensors.index.json": { "bytes": 76212, "sha256": "bfdb536b3ccc4844fc44e9ae018232fd73f65a2b9f01dbf9b6d09d53ae68687c" }, "preprocessor_config.json": { "bytes": 390, "sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516" }, "tokenizer.json": { "bytes": 12809320, "sha256": "0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3" }, "tokenizer_config.json": { "bytes": 17928, "sha256": "b11349aafa7cdc6a320767cf7ceb29ed82f7eda5d65e8e0819e76f0ce947bf27" }, "video_preprocessor_config.json": { "bytes": 385, "sha256": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13" }, "vocab.json": { "bytes": 6722759, "sha256": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003" } }, "source_shards": 130, "tensor_equivalence": { "exact_reference_weight_map": true, "output_index_file_sha256": "06ef64c782c1a5190e803dbf59abaab979f95992edf079dc9c708ec653d8a12f", "output_shard_count": 18, "reference_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "schema_version": 1, "shards": [ { "bytes": 3045232952, "chunk_bytes": 16777216, "coalesced_source_segments": 11, "filename": "model-00001-of-00018.safetensors", "header_length": 7600, "header_sha256": "a69adeeaa18ae523c2a531105648ddb9ac5c20c54c0dc44eaaae012eb7858931", "schema_version": 1, "sha256": "5dc57b22e93ebb1983407023af1f8a320e71ff58f8555e7c91eaaa6787a4ca59", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 186, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 59, "tensors": { "model.language_model.layers.0.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "da43e38b6d314dfa954056feb18935bfa7c76e6f1dc80cd27f1e675fc1c8e4c9", "shape": [ 5120 ], "source_sha256": "da43e38b6d314dfa954056feb18935bfa7c76e6f1dc80cd27f1e675fc1c8e4c9" }, "model.language_model.layers.0.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "0f41b4f02c7093d4f02c13b031b7874f91cedca8f64baa10a2f23766194edc14", "shape": [ 48 ], "source_sha256": "0f41b4f02c7093d4f02c13b031b7874f91cedca8f64baa10a2f23766194edc14" }, "model.language_model.layers.0.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "d206804b904d53714dcfcc88ad0c4615142f03076518f55e762668c51c7da219", "shape": [ 10240, 1, 4 ], "source_sha256": "d206804b904d53714dcfcc88ad0c4615142f03076518f55e762668c51c7da219" }, "model.language_model.layers.0.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "969ce6b2149d20f0c365373fd89613167e373905c15f0e1cf5af62adf52228de", "shape": [ 48 ], "source_sha256": "969ce6b2149d20f0c365373fd89613167e373905c15f0e1cf5af62adf52228de" }, "model.language_model.layers.0.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "bf0cb5689635d5d953aeb3675b60e9e0a56ca385073a4274962faf44180d6164", "shape": [ 48, 5120 ], "source_sha256": "bf0cb5689635d5d953aeb3675b60e9e0a56ca385073a4274962faf44180d6164" }, "model.language_model.layers.0.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "e34db0d462bafe1656312fa24a12c9b823f551a84c0ec0cee3f26128eac26d80", "shape": [ 48, 5120 ], "source_sha256": "e34db0d462bafe1656312fa24a12c9b823f551a84c0ec0cee3f26128eac26d80" }, "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "7bb7d6bb84142415f89475b5e015222f8293cd12caa1486317778fc0086ce0cf", "shape": [ 10240, 5120 ], "source_sha256": "7bb7d6bb84142415f89475b5e015222f8293cd12caa1486317778fc0086ce0cf" }, "model.language_model.layers.0.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "d1e93a122f2e6c30ca3ac80e38820f63947eb6272ebf22e00e3ae8a6cdbbfd89", "shape": [ 6144, 5120 ], "source_sha256": "d1e93a122f2e6c30ca3ac80e38820f63947eb6272ebf22e00e3ae8a6cdbbfd89" }, "model.language_model.layers.0.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "70d11f294923a94aac97bedd27e596dbf496746c6b9e3b2b7c38798a0d2522cc", "shape": [ 128 ], "source_sha256": "70d11f294923a94aac97bedd27e596dbf496746c6b9e3b2b7c38798a0d2522cc" }, "model.language_model.layers.0.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "f66edf4f33ddc51e73500acec715e5a7ea5f26617711a41bd728edfcc0e03511", "shape": [ 5120, 6144 ], "source_sha256": "f66edf4f33ddc51e73500acec715e5a7ea5f26617711a41bd728edfcc0e03511" }, "model.language_model.layers.0.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "bb5eed9b171e1a56cdadd4c87fec2d14322b7ce477f307ec611fccea43e293c8", "shape": [ 5120, 17408 ], "source_sha256": "bb5eed9b171e1a56cdadd4c87fec2d14322b7ce477f307ec611fccea43e293c8" }, "model.language_model.layers.0.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d09a382bb25dc2fe2c50af113b80388076059fe706d0a4e03da20e1fbb74b116", "shape": [ 17408, 5120 ], "source_sha256": "d09a382bb25dc2fe2c50af113b80388076059fe706d0a4e03da20e1fbb74b116" }, "model.language_model.layers.0.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "697acdcd117dfe57488fcbb39e4630fc0f1577b339d9024af997368d892278dd", "shape": [ 17408, 5120 ], "source_sha256": "697acdcd117dfe57488fcbb39e4630fc0f1577b339d9024af997368d892278dd" }, "model.language_model.layers.0.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a1a20246f023bfad0ec3a24c9bf17fd88d638d3190e69266cf29d48205bb4c20", "shape": [ 5120 ], "source_sha256": "a1a20246f023bfad0ec3a24c9bf17fd88d638d3190e69266cf29d48205bb4c20" }, "model.language_model.layers.1.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "bda44bcfb513e657325cf6e785537cdb04e432e469a01978d0bf3f8877061a5f", "shape": [ 5120 ], "source_sha256": "bda44bcfb513e657325cf6e785537cdb04e432e469a01978d0bf3f8877061a5f" }, "model.language_model.layers.1.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "93af28c958f9c0d221dfc978152152cf524f3a924ded54562cbcb11ea3bdf325", "shape": [ 48 ], "source_sha256": "93af28c958f9c0d221dfc978152152cf524f3a924ded54562cbcb11ea3bdf325" }, "model.language_model.layers.1.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "9080640de47f64e432bcface1fcfc89641cbbd04e5ad95d356cec1a0444f6c9c", "shape": [ 10240, 1, 4 ], "source_sha256": "9080640de47f64e432bcface1fcfc89641cbbd04e5ad95d356cec1a0444f6c9c" }, "model.language_model.layers.1.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "73cd8b7f18cd993644fad6090436fb4aead381da196e86a9ca1488d450970120", "shape": [ 48 ], "source_sha256": "73cd8b7f18cd993644fad6090436fb4aead381da196e86a9ca1488d450970120" }, "model.language_model.layers.1.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "ba1ef55359c5ce460caed853a28a4d1bac1c9c5511e65c264dd98790fde2378d", "shape": [ 48, 5120 ], "source_sha256": "ba1ef55359c5ce460caed853a28a4d1bac1c9c5511e65c264dd98790fde2378d" }, "model.language_model.layers.1.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "cb4d5ed0f900789472b41a1538728fb7dfbb3b4ff3504fbfb63658ae98f49a9f", "shape": [ 48, 5120 ], "source_sha256": "cb4d5ed0f900789472b41a1538728fb7dfbb3b4ff3504fbfb63658ae98f49a9f" }, "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "ff4e85e84dafae492427b45e01d5842823ea920a4fc2156218879903c9b61112", "shape": [ 10240, 5120 ], "source_sha256": "ff4e85e84dafae492427b45e01d5842823ea920a4fc2156218879903c9b61112" }, "model.language_model.layers.1.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "f0af36a6e50e7589036836c74ac8f46b2e866c57480529d81961a22756f050aa", "shape": [ 6144, 5120 ], "source_sha256": "f0af36a6e50e7589036836c74ac8f46b2e866c57480529d81961a22756f050aa" }, "model.language_model.layers.1.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "fd2ee76b9b9d37a5649582b580f65b1bca01705390a2d8d6b7140971a441bfb7", "shape": [ 128 ], "source_sha256": "fd2ee76b9b9d37a5649582b580f65b1bca01705390a2d8d6b7140971a441bfb7" }, "model.language_model.layers.1.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "185621809d831f26b8a555d0cb658d6dbccd53b4f660f0d4a685b205906e1269", "shape": [ 5120, 6144 ], "source_sha256": "185621809d831f26b8a555d0cb658d6dbccd53b4f660f0d4a685b205906e1269" }, "model.language_model.layers.1.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f85a54023f8fe341c33bbad29755e7330a3721dc1a51e523aad2a7f63b30ef1b", "shape": [ 5120, 17408 ], "source_sha256": "f85a54023f8fe341c33bbad29755e7330a3721dc1a51e523aad2a7f63b30ef1b" }, "model.language_model.layers.1.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "559442344121dd482c99870420d562de6058bfa69c3328373e5fec5610f56599", "shape": [ 17408, 5120 ], "source_sha256": "559442344121dd482c99870420d562de6058bfa69c3328373e5fec5610f56599" }, "model.language_model.layers.1.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "59a4559bf97776912c8c22fb39da266bf93882ab2f4d38aec7a757973a394c97", "shape": [ 17408, 5120 ], "source_sha256": "59a4559bf97776912c8c22fb39da266bf93882ab2f4d38aec7a757973a394c97" }, "model.language_model.layers.1.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "5afe25fb311b312eb957c23950c37214ea404748e22269967fba9351a0a623b1", "shape": [ 5120 ], "source_sha256": "5afe25fb311b312eb957c23950c37214ea404748e22269967fba9351a0a623b1" }, "model.language_model.layers.2.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "2bb11389e85c17aa6d36fa8622aba836c1e3a1f76db42cf53bac0d4f9b61fc29", "shape": [ 5120 ], "source_sha256": "2bb11389e85c17aa6d36fa8622aba836c1e3a1f76db42cf53bac0d4f9b61fc29" }, "model.language_model.layers.2.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "6451d646f7e0844457076bc44b045feb8f64dc3b58ec8b48e49f0a080c7fa5c4", "shape": [ 48 ], "source_sha256": "6451d646f7e0844457076bc44b045feb8f64dc3b58ec8b48e49f0a080c7fa5c4" }, "model.language_model.layers.2.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "07c29539e50e130f5dc2f9339abd3979567ffa6ff73272d5cea278b149693c3d", "shape": [ 10240, 1, 4 ], "source_sha256": "07c29539e50e130f5dc2f9339abd3979567ffa6ff73272d5cea278b149693c3d" }, "model.language_model.layers.2.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "2981ea3479b1bf7556eaf584f116d0a61a7735c073325d8437742aa4d0f6dc96", "shape": [ 48 ], "source_sha256": "2981ea3479b1bf7556eaf584f116d0a61a7735c073325d8437742aa4d0f6dc96" }, "model.language_model.layers.2.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "d24813f01a5a77cf14df6450a3063cf9946c91ba653813f539a61ab24d29b2be", "shape": [ 48, 5120 ], "source_sha256": "d24813f01a5a77cf14df6450a3063cf9946c91ba653813f539a61ab24d29b2be" }, "model.language_model.layers.2.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "beff055222c52fbe8d2d0dc4eb97f14dc85bcddacd0db3d726adb1b287a4f45e", "shape": [ 48, 5120 ], "source_sha256": "beff055222c52fbe8d2d0dc4eb97f14dc85bcddacd0db3d726adb1b287a4f45e" }, "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "64d73228a178df690e920d5590ead5a576c2a07d86f42493aed1dd9785f912a1", "shape": [ 10240, 5120 ], "source_sha256": "64d73228a178df690e920d5590ead5a576c2a07d86f42493aed1dd9785f912a1" }, "model.language_model.layers.2.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "599ae3afb2500a8c6cfcb5c8917d9d976b576c007f5ef89195f804df518838b2", "shape": [ 6144, 5120 ], "source_sha256": "599ae3afb2500a8c6cfcb5c8917d9d976b576c007f5ef89195f804df518838b2" }, "model.language_model.layers.2.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "3b2f5e3ad26ceb7970100bd8647415666b5429b8f765c631507fdae95aea0386", "shape": [ 128 ], "source_sha256": "3b2f5e3ad26ceb7970100bd8647415666b5429b8f765c631507fdae95aea0386" }, "model.language_model.layers.2.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "6c8ae562c3af7ffc74bde8f7db588830713202e20988f7bb44d39dc12e17b24e", "shape": [ 5120, 6144 ], "source_sha256": "6c8ae562c3af7ffc74bde8f7db588830713202e20988f7bb44d39dc12e17b24e" }, "model.language_model.layers.2.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "1de68846e15088404fc4126cd2628c05e3914265e4d7d53683fa81c1dcf48d29", "shape": [ 5120, 17408 ], "source_sha256": "1de68846e15088404fc4126cd2628c05e3914265e4d7d53683fa81c1dcf48d29" }, "model.language_model.layers.2.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "79dea2490e1cce82705660f8fc3c778996a411d0bc25a536e92844d51690e3de", "shape": [ 17408, 5120 ], "source_sha256": "79dea2490e1cce82705660f8fc3c778996a411d0bc25a536e92844d51690e3de" }, "model.language_model.layers.2.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c4dfe5c9865aa2d1cd1b94f0e7db459dd5f7d39af79908980fda8bec9b7f89b9", "shape": [ 17408, 5120 ], "source_sha256": "c4dfe5c9865aa2d1cd1b94f0e7db459dd5f7d39af79908980fda8bec9b7f89b9" }, "model.language_model.layers.2.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "00048ed3eef05158acd9aa910481f0b9882f476bbf2075a41cf2c169fc3a8ecd", "shape": [ 5120 ], "source_sha256": "00048ed3eef05158acd9aa910481f0b9882f476bbf2075a41cf2c169fc3a8ecd" }, "model.language_model.layers.3.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "10c2d40a86413c652482c5c8e20629309bf37a722a48c3fca4348d86e9d28e8d", "shape": [ 5120 ], "source_sha256": "10c2d40a86413c652482c5c8e20629309bf37a722a48c3fca4348d86e9d28e8d" }, "model.language_model.layers.3.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c1f1e45933bb06bfe0b37a0c7cab4f63c63525c896751459e11e31d055b02b70", "shape": [ 5120, 17408 ], "source_sha256": "c1f1e45933bb06bfe0b37a0c7cab4f63c63525c896751459e11e31d055b02b70" }, "model.language_model.layers.3.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "6d7a64fc3a7ed592e8407ec69f662eaed7dd50976f3d0ff152073a01cc284885", "shape": [ 17408, 5120 ], "source_sha256": "6d7a64fc3a7ed592e8407ec69f662eaed7dd50976f3d0ff152073a01cc284885" }, "model.language_model.layers.3.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "345852c45658ba537c8fc7cf2a9e5bf1e2e71c83e535b3548cd59b441c96fa5a", "shape": [ 17408, 5120 ], "source_sha256": "345852c45658ba537c8fc7cf2a9e5bf1e2e71c83e535b3548cd59b441c96fa5a" }, "model.language_model.layers.3.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "fbbe7631408e20284ae1431c88b9b58151f6a84a70e240cc61b20af9333c082b", "shape": [ 5120 ], "source_sha256": "fbbe7631408e20284ae1431c88b9b58151f6a84a70e240cc61b20af9333c082b" }, "model.language_model.layers.3.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "b46080bc2f1217b8db5df05cc9c6cab7bfa1b6fc7afb492e69a9e8ec2c65c0df", "shape": [ 256 ], "source_sha256": "b46080bc2f1217b8db5df05cc9c6cab7bfa1b6fc7afb492e69a9e8ec2c65c0df" }, "model.language_model.layers.3.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "95e5e660370fe4a3ac582b772c6e4c9ad2da57e982f607cfd94e60b9533d8821", "shape": [ 1024, 5120 ], "source_sha256": "95e5e660370fe4a3ac582b772c6e4c9ad2da57e982f607cfd94e60b9533d8821" }, "model.language_model.layers.3.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "e8bfdf5c6931afe28f45411a1f1ce141bf89a13c7e6394211ef5960af760356b", "shape": [ 5120, 6144 ], "source_sha256": "e8bfdf5c6931afe28f45411a1f1ce141bf89a13c7e6394211ef5960af760356b" }, "model.language_model.layers.3.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "4dfb9b152ad10548a134f39448e62a0c3ddea4d7c79a71ec129ce1603c0cff71", "shape": [ 256 ], "source_sha256": "4dfb9b152ad10548a134f39448e62a0c3ddea4d7c79a71ec129ce1603c0cff71" }, "model.language_model.layers.3.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "1f47bbac85b791180584b7b2c18670fcf876c205f9f638320a11c2e35e6d8179", "shape": [ 12288, 5120 ], "source_sha256": "1f47bbac85b791180584b7b2c18670fcf876c205f9f638320a11c2e35e6d8179" }, "model.language_model.layers.3.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "f2dc09fce8b06662ae4129f4a13f3f3569249299fad2ea4bd29653d58e3ee468", "shape": [ 1024, 5120 ], "source_sha256": "f2dc09fce8b06662ae4129f4a13f3f3569249299fad2ea4bd29653d58e3ee468" }, "model.language_model.layers.4.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "4a5d75d0e5f11d95ed94c557db678a299afb17adf7362484c99b03ee1e92cf23", "shape": [ 5120 ], "source_sha256": "4a5d75d0e5f11d95ed94c557db678a299afb17adf7362484c99b03ee1e92cf23" }, "model.language_model.layers.4.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "577ceefc8c21eedb791ede844edfc3413dc84d8b950ad49589ffc579723da83b", "shape": [ 48 ], "source_sha256": "577ceefc8c21eedb791ede844edfc3413dc84d8b950ad49589ffc579723da83b" }, "model.language_model.layers.4.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "56f8a08aa32ee8d86cff422d4c15a39dbf9781296afd2a1b574edf8cd5b9d655", "shape": [ 10240, 1, 4 ], "source_sha256": "56f8a08aa32ee8d86cff422d4c15a39dbf9781296afd2a1b574edf8cd5b9d655" }, "model.language_model.layers.4.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "a6e5a8003039d222502249bc31db4faa2fde2acbd4fc39554902251ab66d5a12", "shape": [ 48 ], "source_sha256": "a6e5a8003039d222502249bc31db4faa2fde2acbd4fc39554902251ab66d5a12" }, "model.language_model.layers.4.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "a2e22a26b2d4c2cd95ef84703976b6ea057b8004c50a6caff33e5fee52bbe888", "shape": [ 48, 5120 ], "source_sha256": "a2e22a26b2d4c2cd95ef84703976b6ea057b8004c50a6caff33e5fee52bbe888" }, "model.language_model.layers.4.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "66d91d8f53c7bbcebfef282c8986b2303c2afb23834c95bb551e5c803038e75a", "shape": [ 48, 5120 ], "source_sha256": "66d91d8f53c7bbcebfef282c8986b2303c2afb23834c95bb551e5c803038e75a" } } }, { "bytes": 3043080488, "chunk_bytes": 16777216, "coalesced_source_segments": 12, "filename": "model-00002-of-00018.safetensors", "header_length": 6112, "header_sha256": "2416cd78c0d5fd53eb339328c4d2453cf1d78a3c5ba4014bee87c535895cf36b", "schema_version": 1, "sha256": "dbb7cfffb2ec45db6f322311a6478d0785db4818b4ac0346f2f608843dca2cb5", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 187, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 47, "tensors": { "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "377289f07b4e1912c2d2e4b5bd923c1d885799269e4a7efef5dd660117ca977d", "shape": [ 10240, 5120 ], "source_sha256": "377289f07b4e1912c2d2e4b5bd923c1d885799269e4a7efef5dd660117ca977d" }, "model.language_model.layers.4.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "8f2026eadfff6eb5314621d354bdb5beedc6b45ac834605314e6927cfa52b581", "shape": [ 6144, 5120 ], "source_sha256": "8f2026eadfff6eb5314621d354bdb5beedc6b45ac834605314e6927cfa52b581" }, "model.language_model.layers.4.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "22f357ca1c5ec590ca5cfeab248a632ec5fe0e7bec97e6da0b642358fe2b7657", "shape": [ 128 ], "source_sha256": "22f357ca1c5ec590ca5cfeab248a632ec5fe0e7bec97e6da0b642358fe2b7657" }, "model.language_model.layers.4.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "e984112b3f3ead73dfefdddd07dfa188877661f795afa2039e29c141afefdf45", "shape": [ 5120, 6144 ], "source_sha256": "e984112b3f3ead73dfefdddd07dfa188877661f795afa2039e29c141afefdf45" }, "model.language_model.layers.4.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c7f0632137913d4a0eb13a9f9286b479b9e2ed391707910a8b34471cd2fa8564", "shape": [ 5120, 17408 ], "source_sha256": "c7f0632137913d4a0eb13a9f9286b479b9e2ed391707910a8b34471cd2fa8564" }, "model.language_model.layers.4.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b825b75c4e90a9d79563a04238069a0b15d5a0970b6bd7991e9503ffbef53a9e", "shape": [ 17408, 5120 ], "source_sha256": "b825b75c4e90a9d79563a04238069a0b15d5a0970b6bd7991e9503ffbef53a9e" }, "model.language_model.layers.4.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "1fb5ebea9a84711b3ef84751ba2cab0b276cf8a8ee5b4b92dd6fd0721d76caa0", "shape": [ 17408, 5120 ], "source_sha256": "1fb5ebea9a84711b3ef84751ba2cab0b276cf8a8ee5b4b92dd6fd0721d76caa0" }, "model.language_model.layers.4.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "88de157dfe4b25b89a253d178addb4f454744dfd870ce75e853581ff93347682", "shape": [ 5120 ], "source_sha256": "88de157dfe4b25b89a253d178addb4f454744dfd870ce75e853581ff93347682" }, "model.language_model.layers.5.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "50d236fd540255f1fcb28f7f059863f2112eaec02ab66a80bb8f3cb022813414", "shape": [ 5120 ], "source_sha256": "50d236fd540255f1fcb28f7f059863f2112eaec02ab66a80bb8f3cb022813414" }, "model.language_model.layers.5.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "882b9190a3babf299aa115be807510f6b1485bbbc5e3a7636313104583620296", "shape": [ 48 ], "source_sha256": "882b9190a3babf299aa115be807510f6b1485bbbc5e3a7636313104583620296" }, "model.language_model.layers.5.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "1071b086ae0b1a217da8d1b69b77980bfa1d61493fe21c0522b1abdc5856861f", "shape": [ 10240, 1, 4 ], "source_sha256": "1071b086ae0b1a217da8d1b69b77980bfa1d61493fe21c0522b1abdc5856861f" }, "model.language_model.layers.5.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "90ab5aa61398efa57e0e966f96aed3c4d0bdc3b951b6c656397b6d460fc41c95", "shape": [ 48 ], "source_sha256": "90ab5aa61398efa57e0e966f96aed3c4d0bdc3b951b6c656397b6d460fc41c95" }, "model.language_model.layers.5.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "f3470b4317963d3b456765f11342f6e56dfa7a1bbb342160a093d0637c13e986", "shape": [ 48, 5120 ], "source_sha256": "f3470b4317963d3b456765f11342f6e56dfa7a1bbb342160a093d0637c13e986" }, "model.language_model.layers.5.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "61388b983aff6c0798259481ec2a485424b63835215b3caae9760b3fd146330d", "shape": [ 48, 5120 ], "source_sha256": "61388b983aff6c0798259481ec2a485424b63835215b3caae9760b3fd146330d" }, "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "ba76bd689c74b965d99071f86631ad3b07f91e45664d9d725ad07234be21c088", "shape": [ 10240, 5120 ], "source_sha256": "ba76bd689c74b965d99071f86631ad3b07f91e45664d9d725ad07234be21c088" }, "model.language_model.layers.5.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "3419c015543072621b548126471b3a86f0d7c9c445c7e8e37abeb989d036f27f", "shape": [ 6144, 5120 ], "source_sha256": "3419c015543072621b548126471b3a86f0d7c9c445c7e8e37abeb989d036f27f" }, "model.language_model.layers.5.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "b9cafb5cbc635f31bc4fdd4f078e72cf1669633e2f323729ce3b5c18e7955b05", "shape": [ 128 ], "source_sha256": "b9cafb5cbc635f31bc4fdd4f078e72cf1669633e2f323729ce3b5c18e7955b05" }, "model.language_model.layers.5.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7d072e8d99032898842ad29c8b61bc33ab7b84446281b0f6dd780333fb7232cd", "shape": [ 5120, 6144 ], "source_sha256": "7d072e8d99032898842ad29c8b61bc33ab7b84446281b0f6dd780333fb7232cd" }, "model.language_model.layers.5.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "de58af99b93529898bdaa0a31a9493264dfa0ef360418c477fe32d9bb2743b80", "shape": [ 5120, 17408 ], "source_sha256": "de58af99b93529898bdaa0a31a9493264dfa0ef360418c477fe32d9bb2743b80" }, "model.language_model.layers.5.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "30cd0502f5f8d2d36edf542fc5e0f44c2d2987632f479c2e1cd6cbdca3eb39ba", "shape": [ 17408, 5120 ], "source_sha256": "30cd0502f5f8d2d36edf542fc5e0f44c2d2987632f479c2e1cd6cbdca3eb39ba" }, "model.language_model.layers.5.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "093f59ed0bfebaa278c46b86e26dc65660f47ab7346b62878ff856390dc53de8", "shape": [ 17408, 5120 ], "source_sha256": "093f59ed0bfebaa278c46b86e26dc65660f47ab7346b62878ff856390dc53de8" }, "model.language_model.layers.5.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "bd1250da00775e3dac0b82b69150fd5a8bc018f3cbb10c835f524acea41e9f49", "shape": [ 5120 ], "source_sha256": "bd1250da00775e3dac0b82b69150fd5a8bc018f3cbb10c835f524acea41e9f49" }, "model.language_model.layers.6.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "bb1783e5f3690c979021db669478887ea80855fea036557041b019dfdefa0e5b", "shape": [ 5120 ], "source_sha256": "bb1783e5f3690c979021db669478887ea80855fea036557041b019dfdefa0e5b" }, "model.language_model.layers.6.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "bcaf5393259a72b92457a0990b44356619b6c5438dabb70a7ff51f0c013e19f8", "shape": [ 48 ], "source_sha256": "bcaf5393259a72b92457a0990b44356619b6c5438dabb70a7ff51f0c013e19f8" }, "model.language_model.layers.6.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "32162983e404ac67b2414e866926e0c41ed06e4108c59ea0835c2a942027ed99", "shape": [ 10240, 1, 4 ], "source_sha256": "32162983e404ac67b2414e866926e0c41ed06e4108c59ea0835c2a942027ed99" }, "model.language_model.layers.6.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "b5afa18319fa2d538405b7b9bf21757d0821768fa74973a33e882bc920e73bd7", "shape": [ 48 ], "source_sha256": "b5afa18319fa2d538405b7b9bf21757d0821768fa74973a33e882bc920e73bd7" }, "model.language_model.layers.6.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "57d76209aceeb973d102317d2c3f801c7723ff74e245292afbeda3d89e67b7e1", "shape": [ 48, 5120 ], "source_sha256": "57d76209aceeb973d102317d2c3f801c7723ff74e245292afbeda3d89e67b7e1" }, "model.language_model.layers.6.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "6d913ac1e874e906bdafb7599b9bcc94dca948a8a78450f3b4af2c3c920a1539", "shape": [ 48, 5120 ], "source_sha256": "6d913ac1e874e906bdafb7599b9bcc94dca948a8a78450f3b4af2c3c920a1539" }, "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "5f7b544b81416e50c8bddab61b7e3af9ce2b4813cceb3e1f02d427057f91fd9c", "shape": [ 10240, 5120 ], "source_sha256": "5f7b544b81416e50c8bddab61b7e3af9ce2b4813cceb3e1f02d427057f91fd9c" }, "model.language_model.layers.6.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "5135f326f84801610d8e7d3e27f34e8daeefbb4bd63fced09b1763d020799174", "shape": [ 6144, 5120 ], "source_sha256": "5135f326f84801610d8e7d3e27f34e8daeefbb4bd63fced09b1763d020799174" }, "model.language_model.layers.6.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "3c431fbff25f5b220765eee28d68dd764ca50c31e4041315976b40cfaa36b853", "shape": [ 128 ], "source_sha256": "3c431fbff25f5b220765eee28d68dd764ca50c31e4041315976b40cfaa36b853" }, "model.language_model.layers.6.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "423b00003609d3b4a5e277b59ec37a0e7cf43e8e955f79755abc11a736d9d8ec", "shape": [ 5120, 6144 ], "source_sha256": "423b00003609d3b4a5e277b59ec37a0e7cf43e8e955f79755abc11a736d9d8ec" }, "model.language_model.layers.6.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "5a1638b8314197bd221c2e9331bd89086e5f937b5b44f42c910b2691685189be", "shape": [ 5120, 17408 ], "source_sha256": "5a1638b8314197bd221c2e9331bd89086e5f937b5b44f42c910b2691685189be" }, "model.language_model.layers.6.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "4d6db77d5b1f9e15442c20396d6d6ae8a341fa2b0041b518adf2899075b2c04d", "shape": [ 17408, 5120 ], "source_sha256": "4d6db77d5b1f9e15442c20396d6d6ae8a341fa2b0041b518adf2899075b2c04d" }, "model.language_model.layers.6.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "40fcc79b6edc11735190f0cc195f0155997d19930272116d87098451277e4a97", "shape": [ 17408, 5120 ], "source_sha256": "40fcc79b6edc11735190f0cc195f0155997d19930272116d87098451277e4a97" }, "model.language_model.layers.6.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "f2cfae2e212676a7c13b325beedcbe3465b98db87b320256b11e655ce5f394c4", "shape": [ 5120 ], "source_sha256": "f2cfae2e212676a7c13b325beedcbe3465b98db87b320256b11e655ce5f394c4" }, "model.language_model.layers.7.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "84abd496c0142fa0496ed53c34a9ba0d87fec5c84a031a957dcba83d005bab34", "shape": [ 5120 ], "source_sha256": "84abd496c0142fa0496ed53c34a9ba0d87fec5c84a031a957dcba83d005bab34" }, "model.language_model.layers.7.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "88a4ba2607151ee27a4f7d7e1f40127d14a81cca22aaf58dcf2cace380d04e51", "shape": [ 5120, 17408 ], "source_sha256": "88a4ba2607151ee27a4f7d7e1f40127d14a81cca22aaf58dcf2cace380d04e51" }, "model.language_model.layers.7.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "1cf68acac1425db429c886135a9398060f1ed74b7af980f64857fa32e10a072b", "shape": [ 17408, 5120 ], "source_sha256": "1cf68acac1425db429c886135a9398060f1ed74b7af980f64857fa32e10a072b" }, "model.language_model.layers.7.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d830d8e4c5fda892220db2651c913150c54c8c521e980ee20ac8a075993a5690", "shape": [ 17408, 5120 ], "source_sha256": "d830d8e4c5fda892220db2651c913150c54c8c521e980ee20ac8a075993a5690" }, "model.language_model.layers.7.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "67c3ed2741ba44d007fffc91d816a721b323ba57b8f268ae1b428f3090734add", "shape": [ 5120 ], "source_sha256": "67c3ed2741ba44d007fffc91d816a721b323ba57b8f268ae1b428f3090734add" }, "model.language_model.layers.7.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "5e259fa6c80dbd466c3d4ac74d4d3a4eb60a0bb7a22759bc814c539a133bb650", "shape": [ 256 ], "source_sha256": "5e259fa6c80dbd466c3d4ac74d4d3a4eb60a0bb7a22759bc814c539a133bb650" }, "model.language_model.layers.7.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "8ef994757b72ac2804f6d26ac82e0c8306a3ff121702a6471d4ccfb58acbaa09", "shape": [ 1024, 5120 ], "source_sha256": "8ef994757b72ac2804f6d26ac82e0c8306a3ff121702a6471d4ccfb58acbaa09" }, "model.language_model.layers.7.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "20402844104bd3b28da14be3e472a54d55d29b3236b0ef966264d401f54ddd02", "shape": [ 5120, 6144 ], "source_sha256": "20402844104bd3b28da14be3e472a54d55d29b3236b0ef966264d401f54ddd02" }, "model.language_model.layers.7.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "4f76322778a3ee463e6522dc503f241374a24fc73d9226986d51aaebd8499307", "shape": [ 256 ], "source_sha256": "4f76322778a3ee463e6522dc503f241374a24fc73d9226986d51aaebd8499307" }, "model.language_model.layers.7.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "169638cfee437aeab89bda2387a4e0e44dd3981b29629692adbda960208e7459", "shape": [ 12288, 5120 ], "source_sha256": "169638cfee437aeab89bda2387a4e0e44dd3981b29629692adbda960208e7459" }, "model.language_model.layers.7.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "b5ca322fa0f9bc0ff50d0695f0e841f74a84f3b582da75ef6fb4fdc4f1906fbe", "shape": [ 1024, 5120 ], "source_sha256": "b5ca322fa0f9bc0ff50d0695f0e841f74a84f3b582da75ef6fb4fdc4f1906fbe" } } }, { "bytes": 2542796928, "chunk_bytes": 16777216, "coalesced_source_segments": 1, "filename": "model-00003-of-00018.safetensors", "header_length": 120, "header_sha256": "3c841d9b5c2c0c53845f6108adc34dece10cbedbc468be6c7f624210218ced4c", "schema_version": 1, "sha256": "64a59a867e7414771971137481b71deabab8e4f361b7f22dd3a6e5f9c2717b4f", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 152, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 1, "tensors": { "model.language_model.embed_tokens.weight": { "bit_exact": true, "data_bytes": 2542796800, "dtype": "BF16", "output_sha256": "3f24eb1a368b5a8280f0049bf802c080a416733e9e2e56e56046e656c42f842f", "shape": [ 248320, 5120 ], "source_sha256": "3f24eb1a368b5a8280f0049bf802c080a416733e9e2e56e56046e656c42f842f" } } }, { "bytes": 3988973496, "chunk_bytes": 16777216, "coalesced_source_segments": 12, "filename": "model-00004-of-00018.safetensors", "header_length": 9008, "header_sha256": "31ece71a524d1cbcb6a8758921acf11f61122c5706a215b8fcdc4f2048d37f6f", "schema_version": 1, "sha256": "6544a49e77c95c7efd3fd09095634e6edd76f69f3f32820f356507bb4486d699", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 241, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 69, "tensors": { "model.language_model.layers.10.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "b53319ccef267f2e2afacc4f65aaa76936694ffed361d6f70bc39ce427823fbe", "shape": [ 5120 ], "source_sha256": "b53319ccef267f2e2afacc4f65aaa76936694ffed361d6f70bc39ce427823fbe" }, "model.language_model.layers.10.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "ac2743f307f8030bf9b24a2f74a98e3884e594bb7f869249248dfee1a2324945", "shape": [ 48 ], "source_sha256": "ac2743f307f8030bf9b24a2f74a98e3884e594bb7f869249248dfee1a2324945" }, "model.language_model.layers.10.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "3dd983ddcb77d22415f9ee9b3a41cc2bf19588bfee765f3f3bc2354445db9e82", "shape": [ 10240, 1, 4 ], "source_sha256": "3dd983ddcb77d22415f9ee9b3a41cc2bf19588bfee765f3f3bc2354445db9e82" }, "model.language_model.layers.10.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "dfd146ad253d37916919e8a01d2fca6360cb5d29cb677538ec43e8e723fa85ba", "shape": [ 48 ], "source_sha256": "dfd146ad253d37916919e8a01d2fca6360cb5d29cb677538ec43e8e723fa85ba" }, "model.language_model.layers.10.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "a5f95b82134acfb1efdd15e2045df8d5d966eebc06140edeb1e828612c6329cc", "shape": [ 48, 5120 ], "source_sha256": "a5f95b82134acfb1efdd15e2045df8d5d966eebc06140edeb1e828612c6329cc" }, "model.language_model.layers.10.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "5b87190c15d35911cd264cec556489dc0088ae3d83f79324b990cb89069e36b1", "shape": [ 48, 5120 ], "source_sha256": "5b87190c15d35911cd264cec556489dc0088ae3d83f79324b990cb89069e36b1" }, "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "fdbb517cb0c6523bef32ff106e703ea4b13776d24800808948505b7244821366", "shape": [ 10240, 5120 ], "source_sha256": "fdbb517cb0c6523bef32ff106e703ea4b13776d24800808948505b7244821366" }, "model.language_model.layers.10.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7ab6465d319c2d7caa91ebf4f1895200e3a6e239b7080be8779d6dd1a7e8bbc2", "shape": [ 6144, 5120 ], "source_sha256": "7ab6465d319c2d7caa91ebf4f1895200e3a6e239b7080be8779d6dd1a7e8bbc2" }, "model.language_model.layers.10.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "c6fe09399114cacae5e1234d535f801f72cc76ee4e77a711507dd695c72889fe", "shape": [ 128 ], "source_sha256": "c6fe09399114cacae5e1234d535f801f72cc76ee4e77a711507dd695c72889fe" }, "model.language_model.layers.10.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "2978469b1cf62c6a95eb0b7045d15f8f8ee11451fb717a24a7686a4df1ae17b5", "shape": [ 5120, 6144 ], "source_sha256": "2978469b1cf62c6a95eb0b7045d15f8f8ee11451fb717a24a7686a4df1ae17b5" }, "model.language_model.layers.10.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "525ef08b5b1a7f4b6053be19c16baebc8a8fa70d5d4c9bad1643057cc632fafe", "shape": [ 5120, 17408 ], "source_sha256": "525ef08b5b1a7f4b6053be19c16baebc8a8fa70d5d4c9bad1643057cc632fafe" }, "model.language_model.layers.10.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "6201e88d5cf96b30ee9b0a5f3b8bfc828531ad68fc5ebab276c7ba461c0ced4e", "shape": [ 17408, 5120 ], "source_sha256": "6201e88d5cf96b30ee9b0a5f3b8bfc828531ad68fc5ebab276c7ba461c0ced4e" }, "model.language_model.layers.10.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c19520a4c50b62025b9c8adb44fdc62780b48c8127035536be505a408ec76af8", "shape": [ 17408, 5120 ], "source_sha256": "c19520a4c50b62025b9c8adb44fdc62780b48c8127035536be505a408ec76af8" }, "model.language_model.layers.10.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "6020d5f07f4b9a0075cb69f30f2019c777f076929d3c31a0e1c0a03887b45ccc", "shape": [ 5120 ], "source_sha256": "6020d5f07f4b9a0075cb69f30f2019c777f076929d3c31a0e1c0a03887b45ccc" }, "model.language_model.layers.11.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "f960b72c2b399003dd23117a6c7d9aecc608e4c0f526fbd705a7fc14d05e5c11", "shape": [ 5120 ], "source_sha256": "f960b72c2b399003dd23117a6c7d9aecc608e4c0f526fbd705a7fc14d05e5c11" }, "model.language_model.layers.11.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b6046b2eeb48d4a0c937da6829c90fa8084549da66d44037282a22f8d6a7987d", "shape": [ 5120, 17408 ], "source_sha256": "b6046b2eeb48d4a0c937da6829c90fa8084549da66d44037282a22f8d6a7987d" }, "model.language_model.layers.11.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b8ef4dd5746f43ce9b873eae377ff0a63c94f1566a0be5e9001959ea464e0fac", "shape": [ 17408, 5120 ], "source_sha256": "b8ef4dd5746f43ce9b873eae377ff0a63c94f1566a0be5e9001959ea464e0fac" }, "model.language_model.layers.11.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b23facfbc081ab5af6549c8a11c7b53dfaab97f84f61367ec0a5e83bec5ae738", "shape": [ 17408, 5120 ], "source_sha256": "b23facfbc081ab5af6549c8a11c7b53dfaab97f84f61367ec0a5e83bec5ae738" }, "model.language_model.layers.11.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "1686022588b252ce68419b1927a9bdd366b6e167898a1f11e34402fde4103352", "shape": [ 5120 ], "source_sha256": "1686022588b252ce68419b1927a9bdd366b6e167898a1f11e34402fde4103352" }, "model.language_model.layers.11.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "9c2ed53a82ead56c90d48c395121d135ebc90f8e716af8f546e9b33ebe4b1c4a", "shape": [ 256 ], "source_sha256": "9c2ed53a82ead56c90d48c395121d135ebc90f8e716af8f546e9b33ebe4b1c4a" }, "model.language_model.layers.11.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "f02b332d54bca10328716dbeb9442b5afef36e35e668a6309eb7fedf36329fea", "shape": [ 1024, 5120 ], "source_sha256": "f02b332d54bca10328716dbeb9442b5afef36e35e668a6309eb7fedf36329fea" }, "model.language_model.layers.11.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "1708e270e7c7d6500c45403d407fbd3069ba14d716e43367f85ade14abc99cbc", "shape": [ 5120, 6144 ], "source_sha256": "1708e270e7c7d6500c45403d407fbd3069ba14d716e43367f85ade14abc99cbc" }, "model.language_model.layers.11.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "3664876a2df3cde45012cac2bddf0187ef9be703be0706c70d6f70f4a9ed66d1", "shape": [ 256 ], "source_sha256": "3664876a2df3cde45012cac2bddf0187ef9be703be0706c70d6f70f4a9ed66d1" }, "model.language_model.layers.11.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "526a8792e711eb54052e9e877c404c85c51c79ad3042f7f521e45b13a718ff03", "shape": [ 12288, 5120 ], "source_sha256": "526a8792e711eb54052e9e877c404c85c51c79ad3042f7f521e45b13a718ff03" }, "model.language_model.layers.11.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "5f615eb358efdf96643ed703f57b7f0f6283f99a0b46287b37a2f8f132c48e0d", "shape": [ 1024, 5120 ], "source_sha256": "5f615eb358efdf96643ed703f57b7f0f6283f99a0b46287b37a2f8f132c48e0d" }, "model.language_model.layers.12.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ba0dcf7ac3539cd9f3255e10d8342f9362aa1845d261d6950c8cf5170c2bbdc4", "shape": [ 5120 ], "source_sha256": "ba0dcf7ac3539cd9f3255e10d8342f9362aa1845d261d6950c8cf5170c2bbdc4" }, "model.language_model.layers.12.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "783c5f82c28b028660e7532128eda868f544139168586fd1687d71c371c85a46", "shape": [ 48 ], "source_sha256": "783c5f82c28b028660e7532128eda868f544139168586fd1687d71c371c85a46" }, "model.language_model.layers.12.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "2305fca75489007aad99eb4eeb4e1b25de9784de6f0bbe52cb4bbf762b848651", "shape": [ 10240, 1, 4 ], "source_sha256": "2305fca75489007aad99eb4eeb4e1b25de9784de6f0bbe52cb4bbf762b848651" }, "model.language_model.layers.12.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "3256a7215442d56a8cb493d131418368f7f136536a658bcc03bef4ba8c1c36af", "shape": [ 48 ], "source_sha256": "3256a7215442d56a8cb493d131418368f7f136536a658bcc03bef4ba8c1c36af" }, "model.language_model.layers.12.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "7789e4afd0f4a1db6699ffeaad40339e58efde5b758d2a1d4ccb930ba8fb8e59", "shape": [ 48, 5120 ], "source_sha256": "7789e4afd0f4a1db6699ffeaad40339e58efde5b758d2a1d4ccb930ba8fb8e59" }, "model.language_model.layers.12.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "8c9bff5b4d4b1eadab2eb57596fff65b81a5f9755db9ff398df666d286f53331", "shape": [ 48, 5120 ], "source_sha256": "8c9bff5b4d4b1eadab2eb57596fff65b81a5f9755db9ff398df666d286f53331" }, "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "dc2a5258b2089bb5a6429435402367e51b3efd672fab0de70046ebef985ef736", "shape": [ 10240, 5120 ], "source_sha256": "dc2a5258b2089bb5a6429435402367e51b3efd672fab0de70046ebef985ef736" }, "model.language_model.layers.12.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "d633c7e034dcbf4d829254a733b6ec918a008e436493bf224dadfe59c587d725", "shape": [ 6144, 5120 ], "source_sha256": "d633c7e034dcbf4d829254a733b6ec918a008e436493bf224dadfe59c587d725" }, "model.language_model.layers.12.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "0cfdc81ca2696d138c26a27a76bead63234c37203367ad216bace46e1077c812", "shape": [ 128 ], "source_sha256": "0cfdc81ca2696d138c26a27a76bead63234c37203367ad216bace46e1077c812" }, "model.language_model.layers.12.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "65a9d83a77df31bd3a340933f42befb9488948541aaaa5c1928d42f800262c5e", "shape": [ 5120, 6144 ], "source_sha256": "65a9d83a77df31bd3a340933f42befb9488948541aaaa5c1928d42f800262c5e" }, "model.language_model.layers.12.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "35f5e700bb0e680c6c8812d5cbb6323d745d1fbb0ee95738bd76a2e38c760898", "shape": [ 5120, 17408 ], "source_sha256": "35f5e700bb0e680c6c8812d5cbb6323d745d1fbb0ee95738bd76a2e38c760898" }, "model.language_model.layers.12.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "58bb89a06d3c66262727758bac9afbd430255c1f1a2235c6fbca09dda2acd447", "shape": [ 17408, 5120 ], "source_sha256": "58bb89a06d3c66262727758bac9afbd430255c1f1a2235c6fbca09dda2acd447" }, "model.language_model.layers.12.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "e37bd379e8228a1228310d0b0973c7732c01ccfd3eb6f0964117401fa6840c07", "shape": [ 17408, 5120 ], "source_sha256": "e37bd379e8228a1228310d0b0973c7732c01ccfd3eb6f0964117401fa6840c07" }, "model.language_model.layers.12.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "df5d779e5de13d9d5f2f44fab22f98c78790e750bce67f08b07cdf077d118cd0", "shape": [ 5120 ], "source_sha256": "df5d779e5de13d9d5f2f44fab22f98c78790e750bce67f08b07cdf077d118cd0" }, "model.language_model.layers.13.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ce77ab11fe39f63284cc83c70ebf599a166d89465de18a0149af469c9a8b79fe", "shape": [ 5120 ], "source_sha256": "ce77ab11fe39f63284cc83c70ebf599a166d89465de18a0149af469c9a8b79fe" }, "model.language_model.layers.13.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "7e5afa8ab223d5a2aab2f349a4f7bc6e1664a03d6320b84b2e742685b95f3a8d", "shape": [ 48 ], "source_sha256": "7e5afa8ab223d5a2aab2f349a4f7bc6e1664a03d6320b84b2e742685b95f3a8d" }, "model.language_model.layers.13.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "d0896d67fb2697139746f661728937b519bc6b70c42daffdd88581bcd2b67e16", "shape": [ 10240, 1, 4 ], "source_sha256": "d0896d67fb2697139746f661728937b519bc6b70c42daffdd88581bcd2b67e16" }, "model.language_model.layers.13.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "bebeeb01e377c1659427c4e809858c1a02541f69768c18e42ef1842b9d9cf294", "shape": [ 48 ], "source_sha256": "bebeeb01e377c1659427c4e809858c1a02541f69768c18e42ef1842b9d9cf294" }, "model.language_model.layers.13.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "6859027ccc93bfefbe90f81f162d7a89bf5713bebe2e9ea73838493d10b17325", "shape": [ 48, 5120 ], "source_sha256": "6859027ccc93bfefbe90f81f162d7a89bf5713bebe2e9ea73838493d10b17325" }, "model.language_model.layers.13.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "ea05d5323a5095411cdcaa3709bc7c3db4eb19f8fd921485f70959f7a1c52d0a", "shape": [ 48, 5120 ], "source_sha256": "ea05d5323a5095411cdcaa3709bc7c3db4eb19f8fd921485f70959f7a1c52d0a" }, "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "f763aa3b77d3ddf1d032f9a03488391c3e94415de36e7999379a0a05944fd38b", "shape": [ 10240, 5120 ], "source_sha256": "f763aa3b77d3ddf1d032f9a03488391c3e94415de36e7999379a0a05944fd38b" }, "model.language_model.layers.13.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "6e56a5234a14496180e3bfb8fd6192bd058053035c5bbea6e4a23619ef19248a", "shape": [ 6144, 5120 ], "source_sha256": "6e56a5234a14496180e3bfb8fd6192bd058053035c5bbea6e4a23619ef19248a" }, "model.language_model.layers.13.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "6c5af44b8e87880909b5c4a5bf7608f4b637afbbe7cecea93e6e2d94f46d611c", "shape": [ 128 ], "source_sha256": "6c5af44b8e87880909b5c4a5bf7608f4b637afbbe7cecea93e6e2d94f46d611c" }, "model.language_model.layers.13.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "29b072d952004b75ce7f1984a695d48660327249853e817c5051b66955bf7303", "shape": [ 5120, 6144 ], "source_sha256": "29b072d952004b75ce7f1984a695d48660327249853e817c5051b66955bf7303" }, "model.language_model.layers.13.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "aca265210f03b16648cfdbdd43f03dadb016fb0f86c4f0d894a3ee849ed802ae", "shape": [ 5120, 17408 ], "source_sha256": "aca265210f03b16648cfdbdd43f03dadb016fb0f86c4f0d894a3ee849ed802ae" }, "model.language_model.layers.13.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "1bfdd2bc41103b4b11e593f62647400636e235fa7277ccddff7f2ad1370627fe", "shape": [ 17408, 5120 ], "source_sha256": "1bfdd2bc41103b4b11e593f62647400636e235fa7277ccddff7f2ad1370627fe" }, "model.language_model.layers.13.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "3ce0872319dd5805f56fec733fa5c9f1da8b318e8d73cd56b4ae2f2fb8ce8ead", "shape": [ 17408, 5120 ], "source_sha256": "3ce0872319dd5805f56fec733fa5c9f1da8b318e8d73cd56b4ae2f2fb8ce8ead" }, "model.language_model.layers.13.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "e466005ccf7847bfc3034eab1617d224b8c27ac90e2042253175231496f9a25b", "shape": [ 5120 ], "source_sha256": "e466005ccf7847bfc3034eab1617d224b8c27ac90e2042253175231496f9a25b" }, "model.language_model.layers.14.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "e0c888d4adcc41a16b2c108703b88130aa907aed5bf57bf4f51d6b46a02733c4", "shape": [ 5120 ], "source_sha256": "e0c888d4adcc41a16b2c108703b88130aa907aed5bf57bf4f51d6b46a02733c4" }, "model.language_model.layers.14.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "5d715cc765ebbf6a5f4f2f54abe53819557c9ad5549bcd25ec484ded4aae7b54", "shape": [ 48 ], "source_sha256": "5d715cc765ebbf6a5f4f2f54abe53819557c9ad5549bcd25ec484ded4aae7b54" }, "model.language_model.layers.14.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "f059a0f584a86d1498b7a9c28f687a1f1d5f81917956a40e9226f32b11a90936", "shape": [ 10240, 1, 4 ], "source_sha256": "f059a0f584a86d1498b7a9c28f687a1f1d5f81917956a40e9226f32b11a90936" }, "model.language_model.layers.14.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "9cea745e24873170d01a34de16b03f57225e74f63aeb8d9c98a90c9ce057617a", "shape": [ 48 ], "source_sha256": "9cea745e24873170d01a34de16b03f57225e74f63aeb8d9c98a90c9ce057617a" }, "model.language_model.layers.14.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "706262e768852b15941d3ec3a647907a8532ce4d1ea124fef82ad9f1a9ba06bc", "shape": [ 48, 5120 ], "source_sha256": "706262e768852b15941d3ec3a647907a8532ce4d1ea124fef82ad9f1a9ba06bc" }, "model.language_model.layers.14.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "997e5a8943cd047a564264f4f85075d7fad11a426c149aad7dbd58ec94b5d1f9", "shape": [ 48, 5120 ], "source_sha256": "997e5a8943cd047a564264f4f85075d7fad11a426c149aad7dbd58ec94b5d1f9" }, "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "3c1f4c4747f5e448bbf2b90cae72da6440aaf816b6e765ba61243bb81d10acb0", "shape": [ 10240, 5120 ], "source_sha256": "3c1f4c4747f5e448bbf2b90cae72da6440aaf816b6e765ba61243bb81d10acb0" }, "model.language_model.layers.14.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "8160144b4e4c8ba8d8475044fff862247d29f9d83c2937f4fbb5f3b3b05cd9b5", "shape": [ 6144, 5120 ], "source_sha256": "8160144b4e4c8ba8d8475044fff862247d29f9d83c2937f4fbb5f3b3b05cd9b5" }, "model.language_model.layers.14.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "0360bed01c6811e5f9aa3d5e0601cb4bbdba66bc4d5b90932b5237c13ad603f7", "shape": [ 128 ], "source_sha256": "0360bed01c6811e5f9aa3d5e0601cb4bbdba66bc4d5b90932b5237c13ad603f7" }, "model.language_model.layers.14.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "629456749cde7597bfae2588e64e779c763b7bc808c0c22cca6b71c153986eed", "shape": [ 5120, 6144 ], "source_sha256": "629456749cde7597bfae2588e64e779c763b7bc808c0c22cca6b71c153986eed" }, "model.language_model.layers.14.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "87657d14b70d8775b9caf3e6d04f085a5757e653759d5d1b9dd582b0d265a064", "shape": [ 5120, 17408 ], "source_sha256": "87657d14b70d8775b9caf3e6d04f085a5757e653759d5d1b9dd582b0d265a064" }, "model.language_model.layers.14.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "bbf41c0d7006e42ab7cf15069cc826d706142d44f3723cf37154a7d811ca587c", "shape": [ 17408, 5120 ], "source_sha256": "bbf41c0d7006e42ab7cf15069cc826d706142d44f3723cf37154a7d811ca587c" }, "model.language_model.layers.14.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ce76385e48d2b085514fd77c248c6f3ac5416aa3d1bcb627ce26c9590917f4ae", "shape": [ 17408, 5120 ], "source_sha256": "ce76385e48d2b085514fd77c248c6f3ac5416aa3d1bcb627ce26c9590917f4ae" }, "model.language_model.layers.14.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "cf7c08afbde0d966cb5da0e328f4cec8b631bb12518961fea0206ee1b253a4a9", "shape": [ 5120 ], "source_sha256": "cf7c08afbde0d966cb5da0e328f4cec8b631bb12518961fea0206ee1b253a4a9" }, "model.language_model.layers.15.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b03689fc6534fa5db99d22c8c9820f6eaa2ee2d9e62cbeb64dd1434aaa8d23d5", "shape": [ 17408, 5120 ], "source_sha256": "b03689fc6534fa5db99d22c8c9820f6eaa2ee2d9e62cbeb64dd1434aaa8d23d5" }, "model.language_model.layers.15.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "1b2f20a15b9cb0fa530cd5957faac397ef9d154bb56b07b4cb473d5eebdd2969", "shape": [ 5120 ], "source_sha256": "1b2f20a15b9cb0fa530cd5957faac397ef9d154bb56b07b4cb473d5eebdd2969" } } }, { "bytes": 2099340032, "chunk_bytes": 16777216, "coalesced_source_segments": 8, "filename": "model-00005-of-00018.safetensors", "header_length": 4792, "header_sha256": "8637f3f9cee46b1ed29350796afe4d8d0a6b7830c7a6c56ab3ccd6db6de6f94a", "schema_version": 1, "sha256": "ddb724ca400d4d92d614c63da42fdc0aa0d5b7223670d530fa85c4ff59f856ad", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 128, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 37, "tensors": { "model.language_model.layers.15.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "fec9d3dff44685e167529c382236f2d84731b7d81300b2f784c30723c07b7f57", "shape": [ 5120 ], "source_sha256": "fec9d3dff44685e167529c382236f2d84731b7d81300b2f784c30723c07b7f57" }, "model.language_model.layers.15.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f054b588bc771004601b16b5184f39f7abf6c52ab1586d6fdd2e46a9717bc340", "shape": [ 5120, 17408 ], "source_sha256": "f054b588bc771004601b16b5184f39f7abf6c52ab1586d6fdd2e46a9717bc340" }, "model.language_model.layers.15.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "7d78dee084ab636b05a0ef5ea4a82e2113f2cbc5f0e450f9536781e9d0d298a5", "shape": [ 17408, 5120 ], "source_sha256": "7d78dee084ab636b05a0ef5ea4a82e2113f2cbc5f0e450f9536781e9d0d298a5" }, "model.language_model.layers.15.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "f884f323d2fbdbd3e352d819c5fb02946aba83ef96d749254f00c2bc8ea29eb7", "shape": [ 256 ], "source_sha256": "f884f323d2fbdbd3e352d819c5fb02946aba83ef96d749254f00c2bc8ea29eb7" }, "model.language_model.layers.15.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "e8ce0312599ce998b439e4499a306fc634db952934cb69956ff93a446c10e61f", "shape": [ 1024, 5120 ], "source_sha256": "e8ce0312599ce998b439e4499a306fc634db952934cb69956ff93a446c10e61f" }, "model.language_model.layers.15.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "8bf462f8c153958c180e6d4b443d480cca9b0ec7762ad288f3a54e9c3b18173a", "shape": [ 5120, 6144 ], "source_sha256": "8bf462f8c153958c180e6d4b443d480cca9b0ec7762ad288f3a54e9c3b18173a" }, "model.language_model.layers.15.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "c428f00a5c3384a25ff26661157fc3ed988a0dfdaae1c238be755ab82b1e9c86", "shape": [ 256 ], "source_sha256": "c428f00a5c3384a25ff26661157fc3ed988a0dfdaae1c238be755ab82b1e9c86" }, "model.language_model.layers.15.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "3f5c4eb5ea2ae73bbd13cb0dbb83ac15f713a46a72b877d68f2c4152ab4d323a", "shape": [ 12288, 5120 ], "source_sha256": "3f5c4eb5ea2ae73bbd13cb0dbb83ac15f713a46a72b877d68f2c4152ab4d323a" }, "model.language_model.layers.15.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "610dd4be5ce9bd7955e50ac6990087359c044e7fbf5bea3e4a9da140235ad9b5", "shape": [ 1024, 5120 ], "source_sha256": "610dd4be5ce9bd7955e50ac6990087359c044e7fbf5bea3e4a9da140235ad9b5" }, "model.language_model.layers.8.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "4b89a27341d683d88b46c69f7d186ad1ffefff2dcd90f698ce6aff86ff4fcaa9", "shape": [ 5120 ], "source_sha256": "4b89a27341d683d88b46c69f7d186ad1ffefff2dcd90f698ce6aff86ff4fcaa9" }, "model.language_model.layers.8.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "ce3a0d638172f69d24a5c2a6c2a24e794f0503be2bb0ab4a38c9ca11f85d0c44", "shape": [ 48 ], "source_sha256": "ce3a0d638172f69d24a5c2a6c2a24e794f0503be2bb0ab4a38c9ca11f85d0c44" }, "model.language_model.layers.8.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "5b8939100d9479257913de51aacdfbcb0f4b8c196a459185ede739a3992851b4", "shape": [ 10240, 1, 4 ], "source_sha256": "5b8939100d9479257913de51aacdfbcb0f4b8c196a459185ede739a3992851b4" }, "model.language_model.layers.8.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "37a3ed537ae70e831e9e2782ff7cd7f6d2e0e3b2592e0717f2695f319bf8d41d", "shape": [ 48 ], "source_sha256": "37a3ed537ae70e831e9e2782ff7cd7f6d2e0e3b2592e0717f2695f319bf8d41d" }, "model.language_model.layers.8.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "605927dde5041c6fbb3658a55b4b51df67e50fb1a554f31f624b096845ad4f22", "shape": [ 48, 5120 ], "source_sha256": "605927dde5041c6fbb3658a55b4b51df67e50fb1a554f31f624b096845ad4f22" }, "model.language_model.layers.8.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "3678e5926b3551f2861ef3d231479d567d394e9b849f79a6f7b1781f1d4de510", "shape": [ 48, 5120 ], "source_sha256": "3678e5926b3551f2861ef3d231479d567d394e9b849f79a6f7b1781f1d4de510" }, "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "4c368ea0bb28b3ee1f75c692e0cf7f7ddabd4842141f92eb66292df0988822db", "shape": [ 10240, 5120 ], "source_sha256": "4c368ea0bb28b3ee1f75c692e0cf7f7ddabd4842141f92eb66292df0988822db" }, "model.language_model.layers.8.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "b2a0235b4dd75b76e4afdb158a903016c7c4d6e86391d82e2bf9fb46a921734b", "shape": [ 6144, 5120 ], "source_sha256": "b2a0235b4dd75b76e4afdb158a903016c7c4d6e86391d82e2bf9fb46a921734b" }, "model.language_model.layers.8.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "87e3d68e4397c863b51bf7d8af69acdcd57de8a2f7f40400742ca8b99293a494", "shape": [ 128 ], "source_sha256": "87e3d68e4397c863b51bf7d8af69acdcd57de8a2f7f40400742ca8b99293a494" }, "model.language_model.layers.8.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "9a25e3f620171ab903d532504a9efa5d33a1a98a794f50bb8b3bcaa3786da264", "shape": [ 5120, 6144 ], "source_sha256": "9a25e3f620171ab903d532504a9efa5d33a1a98a794f50bb8b3bcaa3786da264" }, "model.language_model.layers.8.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "4a0f328466c06286a5bfaec62b5b766f10908e5efdea3673645e386e7e02b0cf", "shape": [ 5120, 17408 ], "source_sha256": "4a0f328466c06286a5bfaec62b5b766f10908e5efdea3673645e386e7e02b0cf" }, "model.language_model.layers.8.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "4c56d65fe3e2ed72ab1b52bbe1664352d4435dacb0c9df8dc283e28b1036a013", "shape": [ 17408, 5120 ], "source_sha256": "4c56d65fe3e2ed72ab1b52bbe1664352d4435dacb0c9df8dc283e28b1036a013" }, "model.language_model.layers.8.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d4b0293bc5bdddcb5c165c2983f5a4d6e9be56f138cb03f04d7e30867b301482", "shape": [ 17408, 5120 ], "source_sha256": "d4b0293bc5bdddcb5c165c2983f5a4d6e9be56f138cb03f04d7e30867b301482" }, "model.language_model.layers.8.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "9f9b1540341ffed8cb02a81d875d46e86a89a58420c92727b858ea871e77dbe3", "shape": [ 5120 ], "source_sha256": "9f9b1540341ffed8cb02a81d875d46e86a89a58420c92727b858ea871e77dbe3" }, "model.language_model.layers.9.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "2fe515638c23215adce4d1d0a645ddb5e0318617ca88f3a92be4b0801a9558c0", "shape": [ 5120 ], "source_sha256": "2fe515638c23215adce4d1d0a645ddb5e0318617ca88f3a92be4b0801a9558c0" }, "model.language_model.layers.9.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "3af63a784ab66d4746779e35afcc6c68976384f2c1bdd1b6a1eea7e966826384", "shape": [ 48 ], "source_sha256": "3af63a784ab66d4746779e35afcc6c68976384f2c1bdd1b6a1eea7e966826384" }, "model.language_model.layers.9.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "b28da3b85129f730e53da61b2bd5cabdcfcb842e8ccd996427003b60259ab3dc", "shape": [ 10240, 1, 4 ], "source_sha256": "b28da3b85129f730e53da61b2bd5cabdcfcb842e8ccd996427003b60259ab3dc" }, "model.language_model.layers.9.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "90db4f61e1c708001c115276daa864f5a776daa704aab53aeafd38714800cad4", "shape": [ 48 ], "source_sha256": "90db4f61e1c708001c115276daa864f5a776daa704aab53aeafd38714800cad4" }, "model.language_model.layers.9.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "929ece2956193c92b26355cb628e3a623f983b4d6ce33cdc2f23d9bc345f66e8", "shape": [ 48, 5120 ], "source_sha256": "929ece2956193c92b26355cb628e3a623f983b4d6ce33cdc2f23d9bc345f66e8" }, "model.language_model.layers.9.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "670fecb49a196bae24d4bbc37cd5745e0558bf89763c0794cf30f235315e511f", "shape": [ 48, 5120 ], "source_sha256": "670fecb49a196bae24d4bbc37cd5745e0558bf89763c0794cf30f235315e511f" }, "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "c3c528aac165e0b25a3001d95d36971a89f3cccaa7a2d5d7bc815780113da538", "shape": [ 10240, 5120 ], "source_sha256": "c3c528aac165e0b25a3001d95d36971a89f3cccaa7a2d5d7bc815780113da538" }, "model.language_model.layers.9.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "f74411f5d2929692c0619539dbca3f8abf5af1af321c3688f5f2fb480f229201", "shape": [ 6144, 5120 ], "source_sha256": "f74411f5d2929692c0619539dbca3f8abf5af1af321c3688f5f2fb480f229201" }, "model.language_model.layers.9.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "414f2cfcfa80c09f6e3d48156e46b09f7f96963defe4bdbaba5a883a0d2d4629", "shape": [ 128 ], "source_sha256": "414f2cfcfa80c09f6e3d48156e46b09f7f96963defe4bdbaba5a883a0d2d4629" }, "model.language_model.layers.9.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "65b22337645031ad516dc49ace36319b7768075022581e9bacf3c5342b70eb55", "shape": [ 5120, 6144 ], "source_sha256": "65b22337645031ad516dc49ace36319b7768075022581e9bacf3c5342b70eb55" }, "model.language_model.layers.9.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "096af3678772d7309f3a64bf7e20eaf0cb1c5a10e85d6d4d823f82271cdd65b8", "shape": [ 5120, 17408 ], "source_sha256": "096af3678772d7309f3a64bf7e20eaf0cb1c5a10e85d6d4d823f82271cdd65b8" }, "model.language_model.layers.9.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ef07f53b5ee1956282ec7a9f50a1cbe47866e868b254334dfe06d66e69129c16", "shape": [ 17408, 5120 ], "source_sha256": "ef07f53b5ee1956282ec7a9f50a1cbe47866e868b254334dfe06d66e69129c16" }, "model.language_model.layers.9.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "a2439e8aee1c51110e996a6955639ee71005e59860020eaba5db4e7e66d4c392", "shape": [ 17408, 5120 ], "source_sha256": "a2439e8aee1c51110e996a6955639ee71005e59860020eaba5db4e7e66d4c392" }, "model.language_model.layers.9.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ee5b8d8cb17c90babb7d86221e9040960f8f80914ca247d6d5d87bfb6ce9a44b", "shape": [ 5120 ], "source_sha256": "ee5b8d8cb17c90babb7d86221e9040960f8f80914ca247d6d5d87bfb6ce9a44b" } } }, { "bytes": 3979554136, "chunk_bytes": 16777216, "coalesced_source_segments": 14, "filename": "model-00006-of-00018.safetensors", "header_length": 9904, "header_sha256": "d2167f32787bce45ffe2eed473daa512201ab337119e38d6c397286aaaceb7b9", "schema_version": 1, "sha256": "95fda08b98d0992100a60d8a3d14a0d6c740407ee6f2fdc03c79b2fe03ecea2f", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 243, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 76, "tensors": { "model.language_model.layers.16.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "94efdd124c3c2f041a4096559c6a93332b6a07b64eaf3375b8f62f630caf69e9", "shape": [ 5120 ], "source_sha256": "94efdd124c3c2f041a4096559c6a93332b6a07b64eaf3375b8f62f630caf69e9" }, "model.language_model.layers.16.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "8e2040a1db32d6f55db14a9e737e19c346db3e5b9f306cb37c637c3fdabdd1f3", "shape": [ 48 ], "source_sha256": "8e2040a1db32d6f55db14a9e737e19c346db3e5b9f306cb37c637c3fdabdd1f3" }, "model.language_model.layers.16.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "c6934a15000f80faef5c9951d8b1e12d7501f1f9f20960ba049664a8701a8faa", "shape": [ 10240, 1, 4 ], "source_sha256": "c6934a15000f80faef5c9951d8b1e12d7501f1f9f20960ba049664a8701a8faa" }, "model.language_model.layers.16.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "1ff976c35b60500605f31044ca0b6042b2241f9ea0bfb38ea2035e2f1cad070d", "shape": [ 48 ], "source_sha256": "1ff976c35b60500605f31044ca0b6042b2241f9ea0bfb38ea2035e2f1cad070d" }, "model.language_model.layers.16.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "2ceea2a5e24a277f29aa709d4d2c7d8d45a391d7670ea560a5ac5e9e4c9373c6", "shape": [ 48, 5120 ], "source_sha256": "2ceea2a5e24a277f29aa709d4d2c7d8d45a391d7670ea560a5ac5e9e4c9373c6" }, "model.language_model.layers.16.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "c923e5164c9b0749c1e990fab5be9a48fa8c45a7101bb7f805d098a89521f039", "shape": [ 48, 5120 ], "source_sha256": "c923e5164c9b0749c1e990fab5be9a48fa8c45a7101bb7f805d098a89521f039" }, "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "9a3fa47a929c4dbd717d3ae2fc99179b749f863809e36e289b915b6efd6d7306", "shape": [ 10240, 5120 ], "source_sha256": "9a3fa47a929c4dbd717d3ae2fc99179b749f863809e36e289b915b6efd6d7306" }, "model.language_model.layers.16.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "54c90d7c3defa3bbe7f3210bcd89d8f5c09f718ed5fb8e78bcfa0879fe94c2e1", "shape": [ 6144, 5120 ], "source_sha256": "54c90d7c3defa3bbe7f3210bcd89d8f5c09f718ed5fb8e78bcfa0879fe94c2e1" }, "model.language_model.layers.16.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "2d6fb99f4e5b02ac72f8439de9ec1474b4853cb1ebbf4532f9596a7392896f95", "shape": [ 128 ], "source_sha256": "2d6fb99f4e5b02ac72f8439de9ec1474b4853cb1ebbf4532f9596a7392896f95" }, "model.language_model.layers.16.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7995b17044e775f1de3aef3f6245618830608c52a439a832bba16fdb5924e643", "shape": [ 5120, 6144 ], "source_sha256": "7995b17044e775f1de3aef3f6245618830608c52a439a832bba16fdb5924e643" }, "model.language_model.layers.16.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "0512d8795991b96820923370138b15ef07e32510acdb85679930558e2c586528", "shape": [ 5120, 17408 ], "source_sha256": "0512d8795991b96820923370138b15ef07e32510acdb85679930558e2c586528" }, "model.language_model.layers.16.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "709d30ef89e5c7b16e2e4e377d545658c7f73f976910602a13b69960916fa086", "shape": [ 17408, 5120 ], "source_sha256": "709d30ef89e5c7b16e2e4e377d545658c7f73f976910602a13b69960916fa086" }, "model.language_model.layers.16.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "53e8de915361d14866b6ffb52e7482dbe075631c69d25a0bb803ee8df344dd59", "shape": [ 17408, 5120 ], "source_sha256": "53e8de915361d14866b6ffb52e7482dbe075631c69d25a0bb803ee8df344dd59" }, "model.language_model.layers.16.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "116dcf713192afcc554acb3f7494638d4ec1640eaa3c9a892c64df45a626ebe9", "shape": [ 5120 ], "source_sha256": "116dcf713192afcc554acb3f7494638d4ec1640eaa3c9a892c64df45a626ebe9" }, "model.language_model.layers.17.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "79ea56e2a575b58e6750b3504810925fc471bd6f59e472b8ad33db02f09449b5", "shape": [ 5120 ], "source_sha256": "79ea56e2a575b58e6750b3504810925fc471bd6f59e472b8ad33db02f09449b5" }, "model.language_model.layers.17.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "fab8fedc73132bfacacebe438ccdd1fcb8826136589c08beeb7d89d41a91511a", "shape": [ 48 ], "source_sha256": "fab8fedc73132bfacacebe438ccdd1fcb8826136589c08beeb7d89d41a91511a" }, "model.language_model.layers.17.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "96953cb2409f6d2115f98a92106ae5f6fe7354de8d5c00540cc8163c5fb49f73", "shape": [ 10240, 1, 4 ], "source_sha256": "96953cb2409f6d2115f98a92106ae5f6fe7354de8d5c00540cc8163c5fb49f73" }, "model.language_model.layers.17.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "12234f2932fcbb34c803b902b2f26a599e57e895b7587a2029578625b5f7b8bd", "shape": [ 48 ], "source_sha256": "12234f2932fcbb34c803b902b2f26a599e57e895b7587a2029578625b5f7b8bd" }, "model.language_model.layers.17.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "b003de0dc840afded3b6a96b1df66c4239dcd88097f74ccab4c9a9f0dc5195ec", "shape": [ 48, 5120 ], "source_sha256": "b003de0dc840afded3b6a96b1df66c4239dcd88097f74ccab4c9a9f0dc5195ec" }, "model.language_model.layers.17.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "5b8646ab729987960ab841417fd100d6a0aac1076ed599626964dfe0adf760e7", "shape": [ 48, 5120 ], "source_sha256": "5b8646ab729987960ab841417fd100d6a0aac1076ed599626964dfe0adf760e7" }, "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "1d7cfd3cbf83b4547c6b0be8d1646f332da387b49e04762524536c4798abd9c2", "shape": [ 10240, 5120 ], "source_sha256": "1d7cfd3cbf83b4547c6b0be8d1646f332da387b49e04762524536c4798abd9c2" }, "model.language_model.layers.17.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "00cb4c978403d0fb691ce0692acb007836daf72d29c5eb09d76934d4553ea742", "shape": [ 6144, 5120 ], "source_sha256": "00cb4c978403d0fb691ce0692acb007836daf72d29c5eb09d76934d4553ea742" }, "model.language_model.layers.17.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "13269c24f4905ac6cc41f2e25a700f951fd8182fcb0d0f1f8fe9d945cf48aedd", "shape": [ 128 ], "source_sha256": "13269c24f4905ac6cc41f2e25a700f951fd8182fcb0d0f1f8fe9d945cf48aedd" }, "model.language_model.layers.17.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "c3e159d48b818b0debe71bce3232ef01fb72a9b37543f814e2d53c5872f1f8bd", "shape": [ 5120, 6144 ], "source_sha256": "c3e159d48b818b0debe71bce3232ef01fb72a9b37543f814e2d53c5872f1f8bd" }, "model.language_model.layers.17.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ed818355914367b8f123c10dcecfae45ced572fd1774e299e14e0baed3bc4688", "shape": [ 5120, 17408 ], "source_sha256": "ed818355914367b8f123c10dcecfae45ced572fd1774e299e14e0baed3bc4688" }, "model.language_model.layers.17.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "91ac4b5a56384183d9fc555b0db93644254b1926f7d2c5ba3ffec032414a4554", "shape": [ 17408, 5120 ], "source_sha256": "91ac4b5a56384183d9fc555b0db93644254b1926f7d2c5ba3ffec032414a4554" }, "model.language_model.layers.17.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "acbf76a8d4599f9807ef4e4ef4534413b8abddaf67bb10361db1be447144c4df", "shape": [ 17408, 5120 ], "source_sha256": "acbf76a8d4599f9807ef4e4ef4534413b8abddaf67bb10361db1be447144c4df" }, "model.language_model.layers.17.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "1922dfe84d1f56373474ba65b9a74435f813a70a3ab7ba5d000c0e1f6c59db07", "shape": [ 5120 ], "source_sha256": "1922dfe84d1f56373474ba65b9a74435f813a70a3ab7ba5d000c0e1f6c59db07" }, "model.language_model.layers.18.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ce714993f4066a1c35dc75184039d1420053a877a59d2e75aa5cb1b4d1d2be64", "shape": [ 5120 ], "source_sha256": "ce714993f4066a1c35dc75184039d1420053a877a59d2e75aa5cb1b4d1d2be64" }, "model.language_model.layers.18.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "c7fea9843a71d0643e4345d91f38d68eaa45cfe1ebf805fe10d963f63969d8db", "shape": [ 48 ], "source_sha256": "c7fea9843a71d0643e4345d91f38d68eaa45cfe1ebf805fe10d963f63969d8db" }, "model.language_model.layers.18.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "4617efea8f42a6f2ffa473dc9547a17b44cf246681cfc34b7d82cfd8a165ba35", "shape": [ 10240, 1, 4 ], "source_sha256": "4617efea8f42a6f2ffa473dc9547a17b44cf246681cfc34b7d82cfd8a165ba35" }, "model.language_model.layers.18.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "a83c9aaf45f354c32120ae7df3e0ec1c1f35f48e36fab1f87b22f8c7df37c342", "shape": [ 48 ], "source_sha256": "a83c9aaf45f354c32120ae7df3e0ec1c1f35f48e36fab1f87b22f8c7df37c342" }, "model.language_model.layers.18.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "c0792f4e99535684aa1ded9fd7ed8071a5f7c0e7d804713032fbb32b82061018", "shape": [ 48, 5120 ], "source_sha256": "c0792f4e99535684aa1ded9fd7ed8071a5f7c0e7d804713032fbb32b82061018" }, "model.language_model.layers.18.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "f2c87d31953dfa204010648966117fcde028119d4e9e66cc3d132ae4367a457c", "shape": [ 48, 5120 ], "source_sha256": "f2c87d31953dfa204010648966117fcde028119d4e9e66cc3d132ae4367a457c" }, "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "2f29ff5dd8288978af830642f43e4f168e4bab7acf82d6a1922a66c0ba4f617d", "shape": [ 10240, 5120 ], "source_sha256": "2f29ff5dd8288978af830642f43e4f168e4bab7acf82d6a1922a66c0ba4f617d" }, "model.language_model.layers.18.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "68c913ad78aed54892c4d84c1034fdbbf5fd91483bcb20464b0ae8c583788914", "shape": [ 6144, 5120 ], "source_sha256": "68c913ad78aed54892c4d84c1034fdbbf5fd91483bcb20464b0ae8c583788914" }, "model.language_model.layers.18.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "1c790429bb67ee096113dd48bfc66e5d65aca786175ee26d1d91b9b54446fe4f", "shape": [ 128 ], "source_sha256": "1c790429bb67ee096113dd48bfc66e5d65aca786175ee26d1d91b9b54446fe4f" }, "model.language_model.layers.18.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "b16941359b7e07f4401c50cb41032974396d5a090c9678da078b8c79cd08e641", "shape": [ 5120, 6144 ], "source_sha256": "b16941359b7e07f4401c50cb41032974396d5a090c9678da078b8c79cd08e641" }, "model.language_model.layers.18.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "600118d81f46ce0a77bb7bec23bad26f53cfeb8e7b160e465d5c4da235b6c304", "shape": [ 5120, 17408 ], "source_sha256": "600118d81f46ce0a77bb7bec23bad26f53cfeb8e7b160e465d5c4da235b6c304" }, "model.language_model.layers.18.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "7143ea28ead102464b6a73d9392445271d1229be51860408f91632ee914a2e9f", "shape": [ 17408, 5120 ], "source_sha256": "7143ea28ead102464b6a73d9392445271d1229be51860408f91632ee914a2e9f" }, "model.language_model.layers.18.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "7dce72939ed057078109f5ca644cd99d2730f2b2bf21f6436b10dfe278e6dacb", "shape": [ 17408, 5120 ], "source_sha256": "7dce72939ed057078109f5ca644cd99d2730f2b2bf21f6436b10dfe278e6dacb" }, "model.language_model.layers.18.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ef003b02b31cab6ab854a5a926722905eee97f4dcecbe0fcc975e7c9abfebbd6", "shape": [ 5120 ], "source_sha256": "ef003b02b31cab6ab854a5a926722905eee97f4dcecbe0fcc975e7c9abfebbd6" }, "model.language_model.layers.19.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "15ef6c0464afe4e22f549aa2ea821c092b45fb8b275451ccf68db1fa6ebbfcf5", "shape": [ 5120 ], "source_sha256": "15ef6c0464afe4e22f549aa2ea821c092b45fb8b275451ccf68db1fa6ebbfcf5" }, "model.language_model.layers.19.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "2f9cf8bcf0baa6878c78b86fbe8038e41ff5c9f3a3cd53f7037ed8d06d02e52b", "shape": [ 5120, 17408 ], "source_sha256": "2f9cf8bcf0baa6878c78b86fbe8038e41ff5c9f3a3cd53f7037ed8d06d02e52b" }, "model.language_model.layers.19.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f05852d16646740eca9c9fc2c80ab77a8004dd3f13bd6ad1d7c0fe66dc1f6391", "shape": [ 17408, 5120 ], "source_sha256": "f05852d16646740eca9c9fc2c80ab77a8004dd3f13bd6ad1d7c0fe66dc1f6391" }, "model.language_model.layers.19.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c71e993cc30a3349407eb116ffb62bd79a7f8edb7ac64ba3e3cb7cfc1dbcb1a2", "shape": [ 17408, 5120 ], "source_sha256": "c71e993cc30a3349407eb116ffb62bd79a7f8edb7ac64ba3e3cb7cfc1dbcb1a2" }, "model.language_model.layers.19.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "431f79839e792c227d5890ecee5590a09a3a14ee518995ff3041cab690d6723d", "shape": [ 5120 ], "source_sha256": "431f79839e792c227d5890ecee5590a09a3a14ee518995ff3041cab690d6723d" }, "model.language_model.layers.19.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "f0a5994502e6e302a5e8b377c15782c331ff53675adcdf371433f8d92a2e7adc", "shape": [ 256 ], "source_sha256": "f0a5994502e6e302a5e8b377c15782c331ff53675adcdf371433f8d92a2e7adc" }, "model.language_model.layers.19.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "70f86fe69bcb141fcdf8e6f3c4a54a3e9289194f90446b69e00e76824f24da65", "shape": [ 1024, 5120 ], "source_sha256": "70f86fe69bcb141fcdf8e6f3c4a54a3e9289194f90446b69e00e76824f24da65" }, "model.language_model.layers.19.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "389b6673645d0d5bddcb37f0575dd5d13808fdb29a4b392e659d46a1259da954", "shape": [ 5120, 6144 ], "source_sha256": "389b6673645d0d5bddcb37f0575dd5d13808fdb29a4b392e659d46a1259da954" }, "model.language_model.layers.19.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "b44fb2902130a1524e0efd113f17bb073f8d5675c521de3b6f7cf83fb8cde4d4", "shape": [ 256 ], "source_sha256": "b44fb2902130a1524e0efd113f17bb073f8d5675c521de3b6f7cf83fb8cde4d4" }, "model.language_model.layers.19.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "1e4ae3b4d597662e642cf1fa6eab6e5995197b1ad57c4b1b2dbe49bacacfe1dc", "shape": [ 12288, 5120 ], "source_sha256": "1e4ae3b4d597662e642cf1fa6eab6e5995197b1ad57c4b1b2dbe49bacacfe1dc" }, "model.language_model.layers.19.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "f2d3f4a4bef00ded4e383c13778d6bb7d64bd925d3d0bbd55c93341af49f003a", "shape": [ 1024, 5120 ], "source_sha256": "f2d3f4a4bef00ded4e383c13778d6bb7d64bd925d3d0bbd55c93341af49f003a" }, "model.language_model.layers.20.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "5d202b8901528925d1586d8ae93ce0b749cb8b9aa7e002cd1f9caaa9671fcb60", "shape": [ 5120 ], "source_sha256": "5d202b8901528925d1586d8ae93ce0b749cb8b9aa7e002cd1f9caaa9671fcb60" }, "model.language_model.layers.20.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "de0da96a05236e4154de6cdf68f96e4748c4cd91555ff501d74a4410f000ad54", "shape": [ 48 ], "source_sha256": "de0da96a05236e4154de6cdf68f96e4748c4cd91555ff501d74a4410f000ad54" }, "model.language_model.layers.20.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "cc169ad97ea95d5e44b64b9763cf00b9a78288d0aa16af14c9078fa9b5ede7e5", "shape": [ 10240, 1, 4 ], "source_sha256": "cc169ad97ea95d5e44b64b9763cf00b9a78288d0aa16af14c9078fa9b5ede7e5" }, "model.language_model.layers.20.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "63751290e03df4df234444a46320199c75f8caa21c9cc359ffb208360a827e3e", "shape": [ 48 ], "source_sha256": "63751290e03df4df234444a46320199c75f8caa21c9cc359ffb208360a827e3e" }, "model.language_model.layers.20.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "a86c6eb76663ffd611a2d68a6ce5373fcb09adb66ba3888597a2cc508c588b42", "shape": [ 48, 5120 ], "source_sha256": "a86c6eb76663ffd611a2d68a6ce5373fcb09adb66ba3888597a2cc508c588b42" }, "model.language_model.layers.20.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "7ca0124264441cf6c57dc27ac506daee2880e4cd757e225a306da20f99190ff6", "shape": [ 48, 5120 ], "source_sha256": "7ca0124264441cf6c57dc27ac506daee2880e4cd757e225a306da20f99190ff6" }, "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "94329074cf19477d11cf74b003405344c11018ff66878f5f8aaa72d5107f6515", "shape": [ 10240, 5120 ], "source_sha256": "94329074cf19477d11cf74b003405344c11018ff66878f5f8aaa72d5107f6515" }, "model.language_model.layers.20.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "26fbcd85ec0ccfdd7b55104af1f18a2a6e6bb879ffcbe8cf0ad1bf624025af68", "shape": [ 6144, 5120 ], "source_sha256": "26fbcd85ec0ccfdd7b55104af1f18a2a6e6bb879ffcbe8cf0ad1bf624025af68" }, "model.language_model.layers.20.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "c59b1d90e6fa0a74242a9d7e83325199567651f2addad5892369ca9abb42ac2b", "shape": [ 128 ], "source_sha256": "c59b1d90e6fa0a74242a9d7e83325199567651f2addad5892369ca9abb42ac2b" }, "model.language_model.layers.20.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "0e172e346c51e80ad3206980b61aec51e195629262e5436cfa0b8473bfa09115", "shape": [ 5120, 6144 ], "source_sha256": "0e172e346c51e80ad3206980b61aec51e195629262e5436cfa0b8473bfa09115" }, "model.language_model.layers.20.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "e5471803cc34fa0ace1522a37467698f9e2f14f5eaeed992d1d8301587519eab", "shape": [ 5120, 17408 ], "source_sha256": "e5471803cc34fa0ace1522a37467698f9e2f14f5eaeed992d1d8301587519eab" }, "model.language_model.layers.20.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c9cacae5a3a1bf845132b817b170236e0f46981e39012159eac3f7785b200ce8", "shape": [ 17408, 5120 ], "source_sha256": "c9cacae5a3a1bf845132b817b170236e0f46981e39012159eac3f7785b200ce8" }, "model.language_model.layers.20.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ab7218ff0d193a6015521e494a0756a5f6964ec616f1ea1ce06b129bbbf6a9ef", "shape": [ 17408, 5120 ], "source_sha256": "ab7218ff0d193a6015521e494a0756a5f6964ec616f1ea1ce06b129bbbf6a9ef" }, "model.language_model.layers.20.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "c9b6ad54a0ac48b1dcd26e9c25f33e3327273d1038cc65e33f2137eac0e82298", "shape": [ 5120 ], "source_sha256": "c9b6ad54a0ac48b1dcd26e9c25f33e3327273d1038cc65e33f2137eac0e82298" }, "model.language_model.layers.21.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "8fdf4681c645d5a2e43a3130402e2b5db03d920458b084f8739e1f05cff57faa", "shape": [ 5120 ], "source_sha256": "8fdf4681c645d5a2e43a3130402e2b5db03d920458b084f8739e1f05cff57faa" }, "model.language_model.layers.21.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "038898b5202004be244bdc23b66d6f8b6400dbe1eeb79a125b52488b2b80b17d", "shape": [ 48 ], "source_sha256": "038898b5202004be244bdc23b66d6f8b6400dbe1eeb79a125b52488b2b80b17d" }, "model.language_model.layers.21.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "06073e3c8257abb78622fdbfa533cad4e3e29f737ae21ce3ad2eb3f40a4858ea", "shape": [ 10240, 1, 4 ], "source_sha256": "06073e3c8257abb78622fdbfa533cad4e3e29f737ae21ce3ad2eb3f40a4858ea" }, "model.language_model.layers.21.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "54ca75b1d5377065fdacc8fbab42369b0331e5467c66e60922024ed630b0137c", "shape": [ 48 ], "source_sha256": "54ca75b1d5377065fdacc8fbab42369b0331e5467c66e60922024ed630b0137c" }, "model.language_model.layers.21.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "b4c4839d209f0193be25ab7661699d850f1d1d991a51a2a4ff628971756de551", "shape": [ 48, 5120 ], "source_sha256": "b4c4839d209f0193be25ab7661699d850f1d1d991a51a2a4ff628971756de551" }, "model.language_model.layers.21.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "42d5aa55544410aca6cfa73cc378133521474dcbef557baaa4e9af59318e11f7", "shape": [ 48, 5120 ], "source_sha256": "42d5aa55544410aca6cfa73cc378133521474dcbef557baaa4e9af59318e11f7" }, "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "23af8c43c705ed01fe4dc41238caaaa49e51a2d5cb6435d94eb01e6aac2065cf", "shape": [ 10240, 5120 ], "source_sha256": "23af8c43c705ed01fe4dc41238caaaa49e51a2d5cb6435d94eb01e6aac2065cf" }, "model.language_model.layers.21.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "bec65c5f729209d8eb36243480b61d6620c56adbd2ce2f4b0092c039680ac6e7", "shape": [ 6144, 5120 ], "source_sha256": "bec65c5f729209d8eb36243480b61d6620c56adbd2ce2f4b0092c039680ac6e7" }, "model.language_model.layers.21.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "ae9aca79b466acf81cdc6fdb961a0fe96ac347836cc12f1eff739a9b79dd9625", "shape": [ 128 ], "source_sha256": "ae9aca79b466acf81cdc6fdb961a0fe96ac347836cc12f1eff739a9b79dd9625" } } }, { "bytes": 2108759408, "chunk_bytes": 16777216, "coalesced_source_segments": 7, "filename": "model-00007-of-00018.safetensors", "header_length": 3912, "header_sha256": "a2399db4efa62cfc4536b781274d51caf27dc65651806fc2aa47c19172f3ff44", "schema_version": 1, "sha256": "7a6d3b460022bf3b6b0e8df9033aac2cae84de142306f65a44b8bdcee7865d17", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 128, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 30, "tensors": { "model.language_model.layers.21.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "38b9dfd2cf863acda5b914724250a18e3d749a96b0fb19e1448ff28e399165ca", "shape": [ 5120, 6144 ], "source_sha256": "38b9dfd2cf863acda5b914724250a18e3d749a96b0fb19e1448ff28e399165ca" }, "model.language_model.layers.21.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "97acb72dfcd6471a638f0cff6197f7973f58faf083d2cd751da13bed6225331b", "shape": [ 5120, 17408 ], "source_sha256": "97acb72dfcd6471a638f0cff6197f7973f58faf083d2cd751da13bed6225331b" }, "model.language_model.layers.21.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c52bad99fea13541a41654b80644ee650411c8ddf8614ad81e1b1b83a0c51b02", "shape": [ 17408, 5120 ], "source_sha256": "c52bad99fea13541a41654b80644ee650411c8ddf8614ad81e1b1b83a0c51b02" }, "model.language_model.layers.21.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "7fe4dff736c474f777233450e4aed8976af0cb27a8bb8324a6e3e4656c77b9d8", "shape": [ 17408, 5120 ], "source_sha256": "7fe4dff736c474f777233450e4aed8976af0cb27a8bb8324a6e3e4656c77b9d8" }, "model.language_model.layers.21.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "35239ab95eabfc581bde76ad9cc1c5178dd76acc65d1df68ae923f0020923d3a", "shape": [ 5120 ], "source_sha256": "35239ab95eabfc581bde76ad9cc1c5178dd76acc65d1df68ae923f0020923d3a" }, "model.language_model.layers.22.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ce76843c894cce210fb999eba5b88e46a1903be84bc9ac5e80cf96647009de0f", "shape": [ 5120 ], "source_sha256": "ce76843c894cce210fb999eba5b88e46a1903be84bc9ac5e80cf96647009de0f" }, "model.language_model.layers.22.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "36665e4a86704564f632c5d0ea29591b1bafa932940ebb9b86009544fb7834ab", "shape": [ 48 ], "source_sha256": "36665e4a86704564f632c5d0ea29591b1bafa932940ebb9b86009544fb7834ab" }, "model.language_model.layers.22.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "4546659548fd6a7d72f07050f0df46831841aae7fd9f709afb17834adda6d5d3", "shape": [ 10240, 1, 4 ], "source_sha256": "4546659548fd6a7d72f07050f0df46831841aae7fd9f709afb17834adda6d5d3" }, "model.language_model.layers.22.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "de8889935cdcdadadbd1576634bb404e147667265c3f3e4df43dde7e0ccbb6f7", "shape": [ 48 ], "source_sha256": "de8889935cdcdadadbd1576634bb404e147667265c3f3e4df43dde7e0ccbb6f7" }, "model.language_model.layers.22.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "ae771a8116c1b54e74e0b541b6d0f738b48f4a14e7f6c8e277778859b520d276", "shape": [ 48, 5120 ], "source_sha256": "ae771a8116c1b54e74e0b541b6d0f738b48f4a14e7f6c8e277778859b520d276" }, "model.language_model.layers.22.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "403fd2cbe9da5e89ee0cc907df30bea2066323193154716343aba8c7b94ae4d1", "shape": [ 48, 5120 ], "source_sha256": "403fd2cbe9da5e89ee0cc907df30bea2066323193154716343aba8c7b94ae4d1" }, "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "cd87b363593674fed14b296e041eb9691b2535b99965623206a3a1d7fe772b21", "shape": [ 10240, 5120 ], "source_sha256": "cd87b363593674fed14b296e041eb9691b2535b99965623206a3a1d7fe772b21" }, "model.language_model.layers.22.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "5154888bffc21d3499f51cc2c44d0b60405cbb30b1462a89199b2e08d694d530", "shape": [ 6144, 5120 ], "source_sha256": "5154888bffc21d3499f51cc2c44d0b60405cbb30b1462a89199b2e08d694d530" }, "model.language_model.layers.22.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "c5312c0aab602c1628f1776ded8c1c86f816f5f6abeec64765e121384199a9a8", "shape": [ 128 ], "source_sha256": "c5312c0aab602c1628f1776ded8c1c86f816f5f6abeec64765e121384199a9a8" }, "model.language_model.layers.22.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "def39b89516b6ff7e93f08db357f2c84f97cc933794c5c26c7b644bd8563783d", "shape": [ 5120, 6144 ], "source_sha256": "def39b89516b6ff7e93f08db357f2c84f97cc933794c5c26c7b644bd8563783d" }, "model.language_model.layers.22.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "cc2012cccf5239759a051aabe3c68acd2fadcb401992b45d9590f5669600b5f7", "shape": [ 5120, 17408 ], "source_sha256": "cc2012cccf5239759a051aabe3c68acd2fadcb401992b45d9590f5669600b5f7" }, "model.language_model.layers.22.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d4b564c5e97c71c87297cfcb393b116731250b460219717703cd07c0b8286575", "shape": [ 17408, 5120 ], "source_sha256": "d4b564c5e97c71c87297cfcb393b116731250b460219717703cd07c0b8286575" }, "model.language_model.layers.22.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "1400a1b509f5fa1ccd7a88d3e687981b08cad86088fd9b6ad6308eeffdcad841", "shape": [ 17408, 5120 ], "source_sha256": "1400a1b509f5fa1ccd7a88d3e687981b08cad86088fd9b6ad6308eeffdcad841" }, "model.language_model.layers.22.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "3545f4717b2229859d9add9be91f68d12c9d4b42dccd611eb53368080e1f56e4", "shape": [ 5120 ], "source_sha256": "3545f4717b2229859d9add9be91f68d12c9d4b42dccd611eb53368080e1f56e4" }, "model.language_model.layers.23.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "af3658a5245dd17c171111e7353d0f4d00d690e1f3d046f9b8e7abd8eb52a831", "shape": [ 5120 ], "source_sha256": "af3658a5245dd17c171111e7353d0f4d00d690e1f3d046f9b8e7abd8eb52a831" }, "model.language_model.layers.23.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "5f7a7a34fe50e88e4d58e7a1301295b384b07ece1ebe92938204976154fb3b72", "shape": [ 5120, 17408 ], "source_sha256": "5f7a7a34fe50e88e4d58e7a1301295b384b07ece1ebe92938204976154fb3b72" }, "model.language_model.layers.23.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "63fad97f3fdd437c1413b4824f4b336467bebb0e10f937967015114a67f84045", "shape": [ 17408, 5120 ], "source_sha256": "63fad97f3fdd437c1413b4824f4b336467bebb0e10f937967015114a67f84045" }, "model.language_model.layers.23.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f168815b1e88397c5692f288114e07cbd471044db5d565fb1927cfb7a373077c", "shape": [ 17408, 5120 ], "source_sha256": "f168815b1e88397c5692f288114e07cbd471044db5d565fb1927cfb7a373077c" }, "model.language_model.layers.23.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "825ac997d6f06e35c5a94935c983b124e10c1a8ad9e526b67b4130ccd07f1391", "shape": [ 5120 ], "source_sha256": "825ac997d6f06e35c5a94935c983b124e10c1a8ad9e526b67b4130ccd07f1391" }, "model.language_model.layers.23.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "b062ab100b68148092fd9990e1b22932f1acd4da9898f56f3da8237e72040b22", "shape": [ 256 ], "source_sha256": "b062ab100b68148092fd9990e1b22932f1acd4da9898f56f3da8237e72040b22" }, "model.language_model.layers.23.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "07a310927b2a19fc1e7913872d25f3c0d2fdc365a489c8f2399db199666a3588", "shape": [ 1024, 5120 ], "source_sha256": "07a310927b2a19fc1e7913872d25f3c0d2fdc365a489c8f2399db199666a3588" }, "model.language_model.layers.23.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "ff64cb5a5d441f40e5832330c8a5e5d06a22cf756d386d3db2d37d1572fa8bb8", "shape": [ 5120, 6144 ], "source_sha256": "ff64cb5a5d441f40e5832330c8a5e5d06a22cf756d386d3db2d37d1572fa8bb8" }, "model.language_model.layers.23.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "3a2835aad78aff03d769a1cc5a3255d91efe9a28892e39a4e52e51676be01002", "shape": [ 256 ], "source_sha256": "3a2835aad78aff03d769a1cc5a3255d91efe9a28892e39a4e52e51676be01002" }, "model.language_model.layers.23.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "204b64841d366cc056ccd822aa00c8301efcdf777a52101ea5f1e966d35ed859", "shape": [ 12288, 5120 ], "source_sha256": "204b64841d366cc056ccd822aa00c8301efcdf777a52101ea5f1e966d35ed859" }, "model.language_model.layers.23.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "07617ab16078e336e6c35b69b8f9c71dee84a4918030a0ab0d52e72eb4473a51", "shape": [ 1024, 5120 ], "source_sha256": "07617ab16078e336e6c35b69b8f9c71dee84a4918030a0ab0d52e72eb4473a51" } } }, { "bytes": 3979554136, "chunk_bytes": 16777216, "coalesced_source_segments": 13, "filename": "model-00008-of-00018.safetensors", "header_length": 9904, "header_sha256": "d9587c6128a64bf2e49c1d3d0fc467ec794dcd9e1e3e95429c6bb28234f1c74f", "schema_version": 1, "sha256": "5cec2cf589e57fef9f9cbb3df9af4d4468b58304d9238c686f71a6a81418d919", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 242, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 76, "tensors": { "model.language_model.layers.24.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "cd52eccd259fe28d7b75002967b78ad84e7abf207d5c7f6fe78a617d1b98bb0f", "shape": [ 5120 ], "source_sha256": "cd52eccd259fe28d7b75002967b78ad84e7abf207d5c7f6fe78a617d1b98bb0f" }, "model.language_model.layers.24.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "c6cc820ca77f86292d0e482ce64a7d19787076919aab1a0cf7a03b8084ce28e7", "shape": [ 48 ], "source_sha256": "c6cc820ca77f86292d0e482ce64a7d19787076919aab1a0cf7a03b8084ce28e7" }, "model.language_model.layers.24.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "f73fcae66899d820ecfd0a801558d856fa0c6c25e21c1ae8a65441e3508bc0af", "shape": [ 10240, 1, 4 ], "source_sha256": "f73fcae66899d820ecfd0a801558d856fa0c6c25e21c1ae8a65441e3508bc0af" }, "model.language_model.layers.24.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "aab1f2dd563fae0da10e6d016f9e625c76733c5c3f9c818ac4b8c2cdfc21c301", "shape": [ 48 ], "source_sha256": "aab1f2dd563fae0da10e6d016f9e625c76733c5c3f9c818ac4b8c2cdfc21c301" }, "model.language_model.layers.24.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "f544d7c8bf0659d2ce280137dfbb16dcf80494436688049d40ab60bf8d79f2d0", "shape": [ 48, 5120 ], "source_sha256": "f544d7c8bf0659d2ce280137dfbb16dcf80494436688049d40ab60bf8d79f2d0" }, "model.language_model.layers.24.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "0552962da32aec7344e1120f9376f1d1534f9851d957395804539cb2adac4603", "shape": [ 48, 5120 ], "source_sha256": "0552962da32aec7344e1120f9376f1d1534f9851d957395804539cb2adac4603" }, "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "0cfb350ae173f9792ee500a071018e130ce339b402ed107e018f9b16c8218b8f", "shape": [ 10240, 5120 ], "source_sha256": "0cfb350ae173f9792ee500a071018e130ce339b402ed107e018f9b16c8218b8f" }, "model.language_model.layers.24.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "48ab84d72516ffa5d28bfc76d12442a6ebcfeb63e794f7b77bad13a3f616d7db", "shape": [ 6144, 5120 ], "source_sha256": "48ab84d72516ffa5d28bfc76d12442a6ebcfeb63e794f7b77bad13a3f616d7db" }, "model.language_model.layers.24.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "4ffb29d6da9124e929242889ea776ae4e9fff87dda055df7b7cd97cb1b429654", "shape": [ 128 ], "source_sha256": "4ffb29d6da9124e929242889ea776ae4e9fff87dda055df7b7cd97cb1b429654" }, "model.language_model.layers.24.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "2afb5a71b6c2946afeb17e03aad51a454501af74849f9c72c5121c96e9f9036a", "shape": [ 5120, 6144 ], "source_sha256": "2afb5a71b6c2946afeb17e03aad51a454501af74849f9c72c5121c96e9f9036a" }, "model.language_model.layers.24.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "e409961b0b2f432fe4e21bbd03b5f3fd6d5c19a166e8a24150c494ccf54f1f2c", "shape": [ 5120, 17408 ], "source_sha256": "e409961b0b2f432fe4e21bbd03b5f3fd6d5c19a166e8a24150c494ccf54f1f2c" }, "model.language_model.layers.24.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "035f60b8acdbaa5c44e6175ef2a24acac0ddf3c0801a8fd21b80c0cb039b162a", "shape": [ 17408, 5120 ], "source_sha256": "035f60b8acdbaa5c44e6175ef2a24acac0ddf3c0801a8fd21b80c0cb039b162a" }, "model.language_model.layers.24.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "629ca6ce31bbe0046b2a929afb4f30a301e29d60917f7f7739b52422ab94dddf", "shape": [ 17408, 5120 ], "source_sha256": "629ca6ce31bbe0046b2a929afb4f30a301e29d60917f7f7739b52422ab94dddf" }, "model.language_model.layers.24.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "6dfe46e7ecf9fec59cbbf414ee9b2bc9a20fa266a27dbfe72f5cfabeb04199e4", "shape": [ 5120 ], "source_sha256": "6dfe46e7ecf9fec59cbbf414ee9b2bc9a20fa266a27dbfe72f5cfabeb04199e4" }, "model.language_model.layers.25.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "820f4ffeb1a3d2790da060e78571d334be6e2596e2b2c91d4b4bd7b59e8528db", "shape": [ 5120 ], "source_sha256": "820f4ffeb1a3d2790da060e78571d334be6e2596e2b2c91d4b4bd7b59e8528db" }, "model.language_model.layers.25.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "d11e5efbc40e8d3b846d1b6a223756e574f64e535447ffe479fd8585ba3fe03e", "shape": [ 48 ], "source_sha256": "d11e5efbc40e8d3b846d1b6a223756e574f64e535447ffe479fd8585ba3fe03e" }, "model.language_model.layers.25.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "a63094bd3ec9bf6b04a1d05e88ac0ac0f7b2c1dc750ee19c47802423f2b4414a", "shape": [ 10240, 1, 4 ], "source_sha256": "a63094bd3ec9bf6b04a1d05e88ac0ac0f7b2c1dc750ee19c47802423f2b4414a" }, "model.language_model.layers.25.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "fb4d9c9826849187215f6c30d78a62157713e98d8487c407377b34f611231876", "shape": [ 48 ], "source_sha256": "fb4d9c9826849187215f6c30d78a62157713e98d8487c407377b34f611231876" }, "model.language_model.layers.25.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "225b97b8ee1d4ab2a331fa480cbdb61b4405702a757b3bc0b3b6303b1e99fa8f", "shape": [ 48, 5120 ], "source_sha256": "225b97b8ee1d4ab2a331fa480cbdb61b4405702a757b3bc0b3b6303b1e99fa8f" }, "model.language_model.layers.25.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "607f8b98803f3ffc2a7576c702d70d198ad6c17fd60a2266457bcacd28025c4f", "shape": [ 48, 5120 ], "source_sha256": "607f8b98803f3ffc2a7576c702d70d198ad6c17fd60a2266457bcacd28025c4f" }, "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "daa514e782c8aac2b2f42362d0ac54d39e164b2eba0420d1b764642f7ccecbb7", "shape": [ 10240, 5120 ], "source_sha256": "daa514e782c8aac2b2f42362d0ac54d39e164b2eba0420d1b764642f7ccecbb7" }, "model.language_model.layers.25.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "90d9e37ef4544f1b936456ceee0b4b0a376144a7ecc13b8c202af542b904678d", "shape": [ 6144, 5120 ], "source_sha256": "90d9e37ef4544f1b936456ceee0b4b0a376144a7ecc13b8c202af542b904678d" }, "model.language_model.layers.25.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "148cd80127cad9d9f2f1d19223a6ee6fbb78fb8edba949fbbeb6384ca69d65a9", "shape": [ 128 ], "source_sha256": "148cd80127cad9d9f2f1d19223a6ee6fbb78fb8edba949fbbeb6384ca69d65a9" }, "model.language_model.layers.25.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7851189e1ce9e6f5d9b882c9c7987991e10119c532cffab49aa5963fb9e013b4", "shape": [ 5120, 6144 ], "source_sha256": "7851189e1ce9e6f5d9b882c9c7987991e10119c532cffab49aa5963fb9e013b4" }, "model.language_model.layers.25.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "7d54d16fb98ca6ec39b37af44cce32b6d0e3fdc993d27752fbabc9b75ca4e5f1", "shape": [ 5120, 17408 ], "source_sha256": "7d54d16fb98ca6ec39b37af44cce32b6d0e3fdc993d27752fbabc9b75ca4e5f1" }, "model.language_model.layers.25.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "0a9bebf40c707448b452f1f5a3001cef037698270c8c25909702f5765a313697", "shape": [ 17408, 5120 ], "source_sha256": "0a9bebf40c707448b452f1f5a3001cef037698270c8c25909702f5765a313697" }, "model.language_model.layers.25.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "7fd3382995f944711439f419d9e8591cdddeacd1c64abc97bbbd9dfbef8b95e4", "shape": [ 17408, 5120 ], "source_sha256": "7fd3382995f944711439f419d9e8591cdddeacd1c64abc97bbbd9dfbef8b95e4" }, "model.language_model.layers.25.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "45afd24245f5eea30a327f827544be70485b005280b56be89ce75bbf9a359d86", "shape": [ 5120 ], "source_sha256": "45afd24245f5eea30a327f827544be70485b005280b56be89ce75bbf9a359d86" }, "model.language_model.layers.26.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "85a1d3ee2e517834eb791181278009c16bb5d73bba7c3fd20349d01633d951b1", "shape": [ 5120 ], "source_sha256": "85a1d3ee2e517834eb791181278009c16bb5d73bba7c3fd20349d01633d951b1" }, "model.language_model.layers.26.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "2842c9ee2093fb63160f7d3078b0a5102058d537afaf99adc7397cab232f3495", "shape": [ 48 ], "source_sha256": "2842c9ee2093fb63160f7d3078b0a5102058d537afaf99adc7397cab232f3495" }, "model.language_model.layers.26.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "e31d4b24efeb676c6a1231b0aaf3a541e107d055d1ef7e382f59ac48cbc024fd", "shape": [ 10240, 1, 4 ], "source_sha256": "e31d4b24efeb676c6a1231b0aaf3a541e107d055d1ef7e382f59ac48cbc024fd" }, "model.language_model.layers.26.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "0ccf43b6a43a73c4e706774111c6519649e0ab998e86a9a8d2613fc74226e3d9", "shape": [ 48 ], "source_sha256": "0ccf43b6a43a73c4e706774111c6519649e0ab998e86a9a8d2613fc74226e3d9" }, "model.language_model.layers.26.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "e1939f8755c1e4b3b934066369fbb04585f27c40ba9c1eb5dc799f5a7fe5f1bc", "shape": [ 48, 5120 ], "source_sha256": "e1939f8755c1e4b3b934066369fbb04585f27c40ba9c1eb5dc799f5a7fe5f1bc" }, "model.language_model.layers.26.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "194994f9017de5d3e962044cb405decfbf5461f98c53ee08c8ab9a9e527eabbd", "shape": [ 48, 5120 ], "source_sha256": "194994f9017de5d3e962044cb405decfbf5461f98c53ee08c8ab9a9e527eabbd" }, "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "6c86d8704529df5f3ca4a075fdd49f75693c838281015fdf52d7fb32a0d2b52a", "shape": [ 10240, 5120 ], "source_sha256": "6c86d8704529df5f3ca4a075fdd49f75693c838281015fdf52d7fb32a0d2b52a" }, "model.language_model.layers.26.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "3caa9c10b5b8462c6d0814b2c3befd53a92e20293d18a895a66652227da7b875", "shape": [ 6144, 5120 ], "source_sha256": "3caa9c10b5b8462c6d0814b2c3befd53a92e20293d18a895a66652227da7b875" }, "model.language_model.layers.26.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "c77a6f3c5f881f2ab10e8e5e5c91f3d28d14bcd94fe70e6b34857eeb5038b5f1", "shape": [ 128 ], "source_sha256": "c77a6f3c5f881f2ab10e8e5e5c91f3d28d14bcd94fe70e6b34857eeb5038b5f1" }, "model.language_model.layers.26.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7f24996553f34010ca8065c7d6195b92a56ed98475f82ad55d7c10b8e5a67b10", "shape": [ 5120, 6144 ], "source_sha256": "7f24996553f34010ca8065c7d6195b92a56ed98475f82ad55d7c10b8e5a67b10" }, "model.language_model.layers.26.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "6f5bdc483ae31cdf7b315c018542843fc5da6acfbd6558b5fdee6426c410cbd6", "shape": [ 5120, 17408 ], "source_sha256": "6f5bdc483ae31cdf7b315c018542843fc5da6acfbd6558b5fdee6426c410cbd6" }, "model.language_model.layers.26.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "4aab9aae7b006198b682bd56f37f42e974fc0a4b3b9cea727f122dc9479cc80a", "shape": [ 17408, 5120 ], "source_sha256": "4aab9aae7b006198b682bd56f37f42e974fc0a4b3b9cea727f122dc9479cc80a" }, "model.language_model.layers.26.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "151c4085310fefd631dd3e146a3b6550f94ba1b42beec20094e98a1335dd422e", "shape": [ 17408, 5120 ], "source_sha256": "151c4085310fefd631dd3e146a3b6550f94ba1b42beec20094e98a1335dd422e" }, "model.language_model.layers.26.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "4d317218310d3d70e52b16a9ef0c6f2734c2e38977758d904d201f3055b12fe7", "shape": [ 5120 ], "source_sha256": "4d317218310d3d70e52b16a9ef0c6f2734c2e38977758d904d201f3055b12fe7" }, "model.language_model.layers.27.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "cff3b4462a8b9e3d0c706b2fce7ea9bc9221f9207a2e57bbd497da33ebd2ac9f", "shape": [ 5120 ], "source_sha256": "cff3b4462a8b9e3d0c706b2fce7ea9bc9221f9207a2e57bbd497da33ebd2ac9f" }, "model.language_model.layers.27.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "749b07a5711b7ce745a5259af927e5c7a8fbbd598b2a4445ef87efc0f90c8a99", "shape": [ 5120, 17408 ], "source_sha256": "749b07a5711b7ce745a5259af927e5c7a8fbbd598b2a4445ef87efc0f90c8a99" }, "model.language_model.layers.27.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "0fdc9025a06070d28aefb100f1d8aeeb84eb1baf8cc8dfdad463b78b45fd9727", "shape": [ 17408, 5120 ], "source_sha256": "0fdc9025a06070d28aefb100f1d8aeeb84eb1baf8cc8dfdad463b78b45fd9727" }, "model.language_model.layers.27.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "33d7e211a5289c29ca37becb162a40b0b93027ffed8d262b28f5c485051332cf", "shape": [ 17408, 5120 ], "source_sha256": "33d7e211a5289c29ca37becb162a40b0b93027ffed8d262b28f5c485051332cf" }, "model.language_model.layers.27.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "e4948c5c223b7b31c0ef3fc1e73ae73b8b096e33a71b94c50d5ce09996e6b8fd", "shape": [ 5120 ], "source_sha256": "e4948c5c223b7b31c0ef3fc1e73ae73b8b096e33a71b94c50d5ce09996e6b8fd" }, "model.language_model.layers.27.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "8badc1af73efc2a7fe627a5da74904b73819f65f21201e314d2cd5e3c7ede793", "shape": [ 256 ], "source_sha256": "8badc1af73efc2a7fe627a5da74904b73819f65f21201e314d2cd5e3c7ede793" }, "model.language_model.layers.27.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "ae6fdef0a7f0c06a9ac9d556b5f6989c7859e2472a25fc220fcd2eecff227d69", "shape": [ 1024, 5120 ], "source_sha256": "ae6fdef0a7f0c06a9ac9d556b5f6989c7859e2472a25fc220fcd2eecff227d69" }, "model.language_model.layers.27.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "e396de3aa5fd3155894577a30d8e0215b52802655d23f561a380d27e446442a4", "shape": [ 5120, 6144 ], "source_sha256": "e396de3aa5fd3155894577a30d8e0215b52802655d23f561a380d27e446442a4" }, "model.language_model.layers.27.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "99cef3a3aae4e13dda25072ea3840d48f6adae4614351eac72e4936b446e0975", "shape": [ 256 ], "source_sha256": "99cef3a3aae4e13dda25072ea3840d48f6adae4614351eac72e4936b446e0975" }, "model.language_model.layers.27.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "002309cf8663ec1ce3fcdfa1ed13ef84f4ce83d3364c8c4489cc8aed88e619f5", "shape": [ 12288, 5120 ], "source_sha256": "002309cf8663ec1ce3fcdfa1ed13ef84f4ce83d3364c8c4489cc8aed88e619f5" }, "model.language_model.layers.27.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "f932e16b048ab47809650c28e23297cdaa6cc25e8d3c5109b9929b5744ceeeca", "shape": [ 1024, 5120 ], "source_sha256": "f932e16b048ab47809650c28e23297cdaa6cc25e8d3c5109b9929b5744ceeeca" }, "model.language_model.layers.28.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "5fad913437f3552a4403434a18a50bf98995f597669bceec79bf09b8766d1a19", "shape": [ 5120 ], "source_sha256": "5fad913437f3552a4403434a18a50bf98995f597669bceec79bf09b8766d1a19" }, "model.language_model.layers.28.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "425bc20f9177e7962793ffaba4bd33fd227f523eedd50a952d3e01b3e27916c3", "shape": [ 48 ], "source_sha256": "425bc20f9177e7962793ffaba4bd33fd227f523eedd50a952d3e01b3e27916c3" }, "model.language_model.layers.28.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "fcf7051e36540e3b7d9c8b879010b99078dda1e06a2b4ca539cc1b6c52c08477", "shape": [ 10240, 1, 4 ], "source_sha256": "fcf7051e36540e3b7d9c8b879010b99078dda1e06a2b4ca539cc1b6c52c08477" }, "model.language_model.layers.28.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "5865908058b7bca1f28eb70a5ba98038da1a23e7749cc0ea4e099b62718c290e", "shape": [ 48 ], "source_sha256": "5865908058b7bca1f28eb70a5ba98038da1a23e7749cc0ea4e099b62718c290e" }, "model.language_model.layers.28.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "fc557a803aec1160b224b4fa7fc6235aa80b8dab4cee6113596446b97bca2950", "shape": [ 48, 5120 ], "source_sha256": "fc557a803aec1160b224b4fa7fc6235aa80b8dab4cee6113596446b97bca2950" }, "model.language_model.layers.28.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "e9322bf8f5d35d6aadc40d4d75cf05e203546546ce1f8a68cb19c5d98575eef5", "shape": [ 48, 5120 ], "source_sha256": "e9322bf8f5d35d6aadc40d4d75cf05e203546546ce1f8a68cb19c5d98575eef5" }, "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "30b4a1addf6fe04addb8af7b28ac151d521bb5a307adf9a168f570bed95bb5c9", "shape": [ 10240, 5120 ], "source_sha256": "30b4a1addf6fe04addb8af7b28ac151d521bb5a307adf9a168f570bed95bb5c9" }, "model.language_model.layers.28.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "e06a8cd942db3ed158a0599aaeb805c3aebef6513bc1b2d4ac28c8660966f3e7", "shape": [ 6144, 5120 ], "source_sha256": "e06a8cd942db3ed158a0599aaeb805c3aebef6513bc1b2d4ac28c8660966f3e7" }, "model.language_model.layers.28.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "6295510924be73c6a61e9ccfef63d3d3643df7bc32ef0e30123f2cac3a1d8e2b", "shape": [ 128 ], "source_sha256": "6295510924be73c6a61e9ccfef63d3d3643df7bc32ef0e30123f2cac3a1d8e2b" }, "model.language_model.layers.28.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "b764dc3e863b1f8a8e7e14fd328610d10757aa37bd6edd69bc3f2e5564f986ce", "shape": [ 5120, 6144 ], "source_sha256": "b764dc3e863b1f8a8e7e14fd328610d10757aa37bd6edd69bc3f2e5564f986ce" }, "model.language_model.layers.28.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ab1885522626fd37d6b0cd1d035ea4e0a0e0c7e2ba8f0eef305db3c4d45121d4", "shape": [ 5120, 17408 ], "source_sha256": "ab1885522626fd37d6b0cd1d035ea4e0a0e0c7e2ba8f0eef305db3c4d45121d4" }, "model.language_model.layers.28.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "dbbe9d6212946b6c237a0b5bb62c18bd6f788c6721dc7994436bef3f364ba1f3", "shape": [ 17408, 5120 ], "source_sha256": "dbbe9d6212946b6c237a0b5bb62c18bd6f788c6721dc7994436bef3f364ba1f3" }, "model.language_model.layers.28.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c2e2dcd5eb1b9b1fa2c2a1a3c5b5cbb14e142702a7df7e47dac85cd30151f7a1", "shape": [ 17408, 5120 ], "source_sha256": "c2e2dcd5eb1b9b1fa2c2a1a3c5b5cbb14e142702a7df7e47dac85cd30151f7a1" }, "model.language_model.layers.28.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a1809ba8aca6bc49ea13d27c801acfbeb43fea24911d5c8caccdc877f32b4cfb", "shape": [ 5120 ], "source_sha256": "a1809ba8aca6bc49ea13d27c801acfbeb43fea24911d5c8caccdc877f32b4cfb" }, "model.language_model.layers.29.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "521b30cb022ac4628dde056c1cb02e4d445f96fb300d9137d7665ad0a3c4239c", "shape": [ 5120 ], "source_sha256": "521b30cb022ac4628dde056c1cb02e4d445f96fb300d9137d7665ad0a3c4239c" }, "model.language_model.layers.29.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "11ddd87bebd92567f5499fde7fc16add2f6fb59028d9bb31eb871dd4f320e85a", "shape": [ 48 ], "source_sha256": "11ddd87bebd92567f5499fde7fc16add2f6fb59028d9bb31eb871dd4f320e85a" }, "model.language_model.layers.29.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "d468d777faba2bfc8c8b3ac7260a89ab91d96e8ee8039631ea068ec79f944491", "shape": [ 10240, 1, 4 ], "source_sha256": "d468d777faba2bfc8c8b3ac7260a89ab91d96e8ee8039631ea068ec79f944491" }, "model.language_model.layers.29.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "6600c9a5ed26022ba3da56aa2a2dd7bb71ecc9314beb3d4a369e0d98a6b01a9b", "shape": [ 48 ], "source_sha256": "6600c9a5ed26022ba3da56aa2a2dd7bb71ecc9314beb3d4a369e0d98a6b01a9b" }, "model.language_model.layers.29.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "8cd401b875005754b0fe007c976e4993c5e63e6fa6343696edb23b0b4a53fbfa", "shape": [ 48, 5120 ], "source_sha256": "8cd401b875005754b0fe007c976e4993c5e63e6fa6343696edb23b0b4a53fbfa" }, "model.language_model.layers.29.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "ff873e5a638c48b39f6861d2322afed3681758a98efa2a99f358e5d4ac864fe0", "shape": [ 48, 5120 ], "source_sha256": "ff873e5a638c48b39f6861d2322afed3681758a98efa2a99f358e5d4ac864fe0" }, "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "78b61bcf4dcc95cc7b01c6e86e72169361dee481e6e19d9b6bdc92959cc51379", "shape": [ 10240, 5120 ], "source_sha256": "78b61bcf4dcc95cc7b01c6e86e72169361dee481e6e19d9b6bdc92959cc51379" }, "model.language_model.layers.29.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "4b5a530b775af7299bad5ffa45df795d9c8d6d5a7e38f69a1157dbf53f59a438", "shape": [ 6144, 5120 ], "source_sha256": "4b5a530b775af7299bad5ffa45df795d9c8d6d5a7e38f69a1157dbf53f59a438" }, "model.language_model.layers.29.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "7948b9a39104e29d6994cbb4e02e66c5007d972a74cf44d3f33880a4e42d6f0c", "shape": [ 128 ], "source_sha256": "7948b9a39104e29d6994cbb4e02e66c5007d972a74cf44d3f33880a4e42d6f0c" } } }, { "bytes": 2108759408, "chunk_bytes": 16777216, "coalesced_source_segments": 8, "filename": "model-00009-of-00018.safetensors", "header_length": 3912, "header_sha256": "9be2854f633924703f12d624cae1acae85ac6bb86803928958940ccc02368a0e", "schema_version": 1, "sha256": "b47a112b7e024943167d72d6da104c7bc8617e7b78dde360c8578368a8679ec5", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 129, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 30, "tensors": { "model.language_model.layers.29.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "e8de2293f775641a51df04be2b33660095f8a2d5eeebc9b0c7fd821ba8975207", "shape": [ 5120, 6144 ], "source_sha256": "e8de2293f775641a51df04be2b33660095f8a2d5eeebc9b0c7fd821ba8975207" }, "model.language_model.layers.29.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "dee870aa8c40bfc12e48c8c15cb5094749a80e48c2adae641543de9ffd55c7e8", "shape": [ 5120, 17408 ], "source_sha256": "dee870aa8c40bfc12e48c8c15cb5094749a80e48c2adae641543de9ffd55c7e8" }, "model.language_model.layers.29.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "0c80475393c1f583d7e63181de73b13b05ac455e66edda9958ea75431d8449b7", "shape": [ 17408, 5120 ], "source_sha256": "0c80475393c1f583d7e63181de73b13b05ac455e66edda9958ea75431d8449b7" }, "model.language_model.layers.29.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "6d1c2c21a1ba454e5ac47432059ab961770f10a086c3b5bfbb19a85a762800ba", "shape": [ 17408, 5120 ], "source_sha256": "6d1c2c21a1ba454e5ac47432059ab961770f10a086c3b5bfbb19a85a762800ba" }, "model.language_model.layers.29.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "d595cb7947f6bf34d6f0d747956d82d12b2ab7afbdf405c99fdef3f6ff15fdb9", "shape": [ 5120 ], "source_sha256": "d595cb7947f6bf34d6f0d747956d82d12b2ab7afbdf405c99fdef3f6ff15fdb9" }, "model.language_model.layers.30.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "9e35c4c7131e5e870d3f8096dd68e6761fb0a3a51a59ab7d922189ad93a08c8c", "shape": [ 5120 ], "source_sha256": "9e35c4c7131e5e870d3f8096dd68e6761fb0a3a51a59ab7d922189ad93a08c8c" }, "model.language_model.layers.30.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "fa04c3b1734a69a088fd7d04aad89f5eca0ee50b46a5dfb3caf136ffe97f7398", "shape": [ 48 ], "source_sha256": "fa04c3b1734a69a088fd7d04aad89f5eca0ee50b46a5dfb3caf136ffe97f7398" }, "model.language_model.layers.30.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "d8e485955d4b71d9fd7087df4b7c4f81313034b6849cd854c51c759942baa67e", "shape": [ 10240, 1, 4 ], "source_sha256": "d8e485955d4b71d9fd7087df4b7c4f81313034b6849cd854c51c759942baa67e" }, "model.language_model.layers.30.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "d5bf9b74604025372334c1013775c6030dbed067d5ee532c77e6fd4df046aae4", "shape": [ 48 ], "source_sha256": "d5bf9b74604025372334c1013775c6030dbed067d5ee532c77e6fd4df046aae4" }, "model.language_model.layers.30.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "d5530ed49bc48fd20c2934b0b50e22108e6be4b9238950a90ec864e901f89631", "shape": [ 48, 5120 ], "source_sha256": "d5530ed49bc48fd20c2934b0b50e22108e6be4b9238950a90ec864e901f89631" }, "model.language_model.layers.30.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "1afb16ca354d39c91fcba93960f4365670fc3abedc9fbb430222b5170651f63c", "shape": [ 48, 5120 ], "source_sha256": "1afb16ca354d39c91fcba93960f4365670fc3abedc9fbb430222b5170651f63c" }, "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "906222115c25ec6786366becdacd33d57b31544c1488ff2eef678c5fbebdc177", "shape": [ 10240, 5120 ], "source_sha256": "906222115c25ec6786366becdacd33d57b31544c1488ff2eef678c5fbebdc177" }, "model.language_model.layers.30.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "3a661a091247bae6b4f1341b3d8c4c3cf10511ba2829205b8151f03f098c6670", "shape": [ 6144, 5120 ], "source_sha256": "3a661a091247bae6b4f1341b3d8c4c3cf10511ba2829205b8151f03f098c6670" }, "model.language_model.layers.30.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "ee71359a54afabe6df0eee185c16d6258ff2112c1006e35272120067915ea8f3", "shape": [ 128 ], "source_sha256": "ee71359a54afabe6df0eee185c16d6258ff2112c1006e35272120067915ea8f3" }, "model.language_model.layers.30.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "9eb45fdf90423261c03bd382e7d3901d3e0f4f7ca97f55a635140563c769cf7a", "shape": [ 5120, 6144 ], "source_sha256": "9eb45fdf90423261c03bd382e7d3901d3e0f4f7ca97f55a635140563c769cf7a" }, "model.language_model.layers.30.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b7bfcd9953217755e2628cf72c333814c1ff1d93cd83213558108a609f5abb65", "shape": [ 5120, 17408 ], "source_sha256": "b7bfcd9953217755e2628cf72c333814c1ff1d93cd83213558108a609f5abb65" }, "model.language_model.layers.30.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "5f85c87083cfdbc307ab91b31231863b59c3dc478aff8dcb6ecc0e91f8195ed5", "shape": [ 17408, 5120 ], "source_sha256": "5f85c87083cfdbc307ab91b31231863b59c3dc478aff8dcb6ecc0e91f8195ed5" }, "model.language_model.layers.30.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "457d3f503b2f98fb27ee69408f4b15dec246f60cc81d33ea416b3c163d233608", "shape": [ 17408, 5120 ], "source_sha256": "457d3f503b2f98fb27ee69408f4b15dec246f60cc81d33ea416b3c163d233608" }, "model.language_model.layers.30.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "fa87042fdac25f02739ecbaa2b160c8ef62bed1054f79153774cddbc510cb2aa", "shape": [ 5120 ], "source_sha256": "fa87042fdac25f02739ecbaa2b160c8ef62bed1054f79153774cddbc510cb2aa" }, "model.language_model.layers.31.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "e03c1cda88317912d5f3fe71949bb136a6e1a6c5164d1e97e87d5171bb0f9f21", "shape": [ 5120 ], "source_sha256": "e03c1cda88317912d5f3fe71949bb136a6e1a6c5164d1e97e87d5171bb0f9f21" }, "model.language_model.layers.31.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d6d4b74ef726ba72d6aaf769608e303eadfc4e042ed7141a44e6e9f98bb983ec", "shape": [ 5120, 17408 ], "source_sha256": "d6d4b74ef726ba72d6aaf769608e303eadfc4e042ed7141a44e6e9f98bb983ec" }, "model.language_model.layers.31.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "a4851ee444a0a2fa8958682a1cfef4fd9f4bf2489232355e3e72485a6bd163e9", "shape": [ 17408, 5120 ], "source_sha256": "a4851ee444a0a2fa8958682a1cfef4fd9f4bf2489232355e3e72485a6bd163e9" }, "model.language_model.layers.31.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "2963b234602861d6a8fe4ffb8d61fff80badefc6982c0bb4c9f6bec8d2d2987d", "shape": [ 17408, 5120 ], "source_sha256": "2963b234602861d6a8fe4ffb8d61fff80badefc6982c0bb4c9f6bec8d2d2987d" }, "model.language_model.layers.31.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "f5ed1f6eaf8803da62aabe65966eefc0fc3e4e47f4db1638de60bae0e25267c6", "shape": [ 5120 ], "source_sha256": "f5ed1f6eaf8803da62aabe65966eefc0fc3e4e47f4db1638de60bae0e25267c6" }, "model.language_model.layers.31.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "ca7aacf4db64c23aea06abff95a349f98031d3fc6bc5ae08be4e5e6485ab9c4c", "shape": [ 256 ], "source_sha256": "ca7aacf4db64c23aea06abff95a349f98031d3fc6bc5ae08be4e5e6485ab9c4c" }, "model.language_model.layers.31.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "f41323f68cfbde140dd6310055fe2fb5c96276bffda73fbf05f43872ff1645a9", "shape": [ 1024, 5120 ], "source_sha256": "f41323f68cfbde140dd6310055fe2fb5c96276bffda73fbf05f43872ff1645a9" }, "model.language_model.layers.31.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "9b2d8ee94b88cb7be27a9b052214c55366af155ef67fb7d94b24ca1b56bdca65", "shape": [ 5120, 6144 ], "source_sha256": "9b2d8ee94b88cb7be27a9b052214c55366af155ef67fb7d94b24ca1b56bdca65" }, "model.language_model.layers.31.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "bb1d6872ebf6683ed08144f611b2bdc45767cf1bf60a52ebdad53e1002545b01", "shape": [ 256 ], "source_sha256": "bb1d6872ebf6683ed08144f611b2bdc45767cf1bf60a52ebdad53e1002545b01" }, "model.language_model.layers.31.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "bfa69d456cf98de9dcfd94e61abf5463e97481aba08e307c1df40d318c28e10d", "shape": [ 12288, 5120 ], "source_sha256": "bfa69d456cf98de9dcfd94e61abf5463e97481aba08e307c1df40d318c28e10d" }, "model.language_model.layers.31.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "80e11b8c542c936d54845682d2ff8580e058df68f58a61f0caa4ef067f066198", "shape": [ 1024, 5120 ], "source_sha256": "80e11b8c542c936d54845682d2ff8580e058df68f58a61f0caa4ef067f066198" } } }, { "bytes": 3979554136, "chunk_bytes": 16777216, "coalesced_source_segments": 13, "filename": "model-00010-of-00018.safetensors", "header_length": 9904, "header_sha256": "40c11a65f476dd04ef8a0be3d7b14ccae09877ee459f586c73c16370a75662f0", "schema_version": 1, "sha256": "202749a3f61f9f8e8893c58f4d7052a8c165d0a07ba56928edc87b48344e83da", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 242, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 76, "tensors": { "model.language_model.layers.32.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "d82cb3dec25feb103cb30fe504c3f2887d84a1aba2febe9d5430d0b92fb55f42", "shape": [ 5120 ], "source_sha256": "d82cb3dec25feb103cb30fe504c3f2887d84a1aba2febe9d5430d0b92fb55f42" }, "model.language_model.layers.32.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "fdc7eb24ce6ac09af25cf9a145c4ffa63fe2ada8f83f6894afccb04625e571ea", "shape": [ 48 ], "source_sha256": "fdc7eb24ce6ac09af25cf9a145c4ffa63fe2ada8f83f6894afccb04625e571ea" }, "model.language_model.layers.32.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "039d4eecda3a01f9e8bee41684208686adf263eed3c538ba7170a408fc534479", "shape": [ 10240, 1, 4 ], "source_sha256": "039d4eecda3a01f9e8bee41684208686adf263eed3c538ba7170a408fc534479" }, "model.language_model.layers.32.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "748d8cb453a913a162169d167a8ee937790b1949f0509e2162c5d586978c2ad2", "shape": [ 48 ], "source_sha256": "748d8cb453a913a162169d167a8ee937790b1949f0509e2162c5d586978c2ad2" }, "model.language_model.layers.32.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "2f7cdb167e022875435b2999ba9712b2e5383060d91bc69e00e11884c29ab0ff", "shape": [ 48, 5120 ], "source_sha256": "2f7cdb167e022875435b2999ba9712b2e5383060d91bc69e00e11884c29ab0ff" }, "model.language_model.layers.32.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "5d04b996487ef7ff41413eda2c5641b471e11c686dca080595fb2cf77e21cc0a", "shape": [ 48, 5120 ], "source_sha256": "5d04b996487ef7ff41413eda2c5641b471e11c686dca080595fb2cf77e21cc0a" }, "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "c6b27bd92ef889e0e6bfa8ab12ca4fc8e5710b3662e90be76f20f368b3993a9f", "shape": [ 10240, 5120 ], "source_sha256": "c6b27bd92ef889e0e6bfa8ab12ca4fc8e5710b3662e90be76f20f368b3993a9f" }, "model.language_model.layers.32.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "90b22a1fba52d354b570cafcb5c685168b69e2e7a3d79b2af4fca15b186be04e", "shape": [ 6144, 5120 ], "source_sha256": "90b22a1fba52d354b570cafcb5c685168b69e2e7a3d79b2af4fca15b186be04e" }, "model.language_model.layers.32.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "fe385efdd03c33ac0f17d000ae6bca9d8779b3dccfa46268d04b78d01c534a11", "shape": [ 128 ], "source_sha256": "fe385efdd03c33ac0f17d000ae6bca9d8779b3dccfa46268d04b78d01c534a11" }, "model.language_model.layers.32.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "4783c34a2d69b41fe255b1cdf2a9e07755bc4a9a8de0a534da21eb0e5dc58e0c", "shape": [ 5120, 6144 ], "source_sha256": "4783c34a2d69b41fe255b1cdf2a9e07755bc4a9a8de0a534da21eb0e5dc58e0c" }, "model.language_model.layers.32.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f44afc88303541a3eca6291a8e2840baafb9f736110ed042610a7414b01d5314", "shape": [ 5120, 17408 ], "source_sha256": "f44afc88303541a3eca6291a8e2840baafb9f736110ed042610a7414b01d5314" }, "model.language_model.layers.32.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "000a95ab9ec339e14eaf1bb200ae5751847f5158014131bba838860d590afcf9", "shape": [ 17408, 5120 ], "source_sha256": "000a95ab9ec339e14eaf1bb200ae5751847f5158014131bba838860d590afcf9" }, "model.language_model.layers.32.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "cc98ca1a04ae581a4c4a22848d85c66690cc699d3d33eb186fededd9becf2717", "shape": [ 17408, 5120 ], "source_sha256": "cc98ca1a04ae581a4c4a22848d85c66690cc699d3d33eb186fededd9becf2717" }, "model.language_model.layers.32.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "33b199af8953e14d1d43e35e56ca37ba57b80893a0da1e367243f62320c237b3", "shape": [ 5120 ], "source_sha256": "33b199af8953e14d1d43e35e56ca37ba57b80893a0da1e367243f62320c237b3" }, "model.language_model.layers.33.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "d5f3cb4b432d48b4ccd504c3a2230c9be4783a2687e18bfb2fe5f51c6d60a3f3", "shape": [ 5120 ], "source_sha256": "d5f3cb4b432d48b4ccd504c3a2230c9be4783a2687e18bfb2fe5f51c6d60a3f3" }, "model.language_model.layers.33.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "75c39d610721d12e37c9aeee849d00071e3d4ce5b8b52579b817abbf911625f4", "shape": [ 48 ], "source_sha256": "75c39d610721d12e37c9aeee849d00071e3d4ce5b8b52579b817abbf911625f4" }, "model.language_model.layers.33.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "ae5c9eb9bcfd33ce8e5dd3f52cad5491752ba9537e64317524e15668c44e9fe3", "shape": [ 10240, 1, 4 ], "source_sha256": "ae5c9eb9bcfd33ce8e5dd3f52cad5491752ba9537e64317524e15668c44e9fe3" }, "model.language_model.layers.33.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "6acb415514eb5a07a6d70594227a59785b7dc2f13f19dc9b444d9f36d782d8af", "shape": [ 48 ], "source_sha256": "6acb415514eb5a07a6d70594227a59785b7dc2f13f19dc9b444d9f36d782d8af" }, "model.language_model.layers.33.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "8a8b9dc0709797ba4052fa4a9b14ceabb0c38dfc293f5d55faada18710f3e698", "shape": [ 48, 5120 ], "source_sha256": "8a8b9dc0709797ba4052fa4a9b14ceabb0c38dfc293f5d55faada18710f3e698" }, "model.language_model.layers.33.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "09f41a6514c721c8f7664d6a22a989c863a2409c218480f9c075cca10fbcefa4", "shape": [ 48, 5120 ], "source_sha256": "09f41a6514c721c8f7664d6a22a989c863a2409c218480f9c075cca10fbcefa4" }, "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "f3166e4ad481510c8a74bd66b8a6d0b5d5e9b106d4029bdfb107366f970f6c4e", "shape": [ 10240, 5120 ], "source_sha256": "f3166e4ad481510c8a74bd66b8a6d0b5d5e9b106d4029bdfb107366f970f6c4e" }, "model.language_model.layers.33.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "a735592c1523196589b2b1ef98daed786d4cef5598fecd7b429f0d21b6b71baf", "shape": [ 6144, 5120 ], "source_sha256": "a735592c1523196589b2b1ef98daed786d4cef5598fecd7b429f0d21b6b71baf" }, "model.language_model.layers.33.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "b87d8fb9208cb6ea5a1306c205ca29617cdcb023c8131e190cb890cd4deb4b19", "shape": [ 128 ], "source_sha256": "b87d8fb9208cb6ea5a1306c205ca29617cdcb023c8131e190cb890cd4deb4b19" }, "model.language_model.layers.33.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "4c6be837d4670bffaa9d69637e7cbb135348285c689e1c713629dacd1d4a8724", "shape": [ 5120, 6144 ], "source_sha256": "4c6be837d4670bffaa9d69637e7cbb135348285c689e1c713629dacd1d4a8724" }, "model.language_model.layers.33.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "adf8a287defd9ab9ea7f3c54d4e086fec0e597f46b7e696d415a84857f6284b1", "shape": [ 5120, 17408 ], "source_sha256": "adf8a287defd9ab9ea7f3c54d4e086fec0e597f46b7e696d415a84857f6284b1" }, "model.language_model.layers.33.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "aa0587b7490f706a99418eb84c423b262fd895a83d57ef6b4751e6ee88599f32", "shape": [ 17408, 5120 ], "source_sha256": "aa0587b7490f706a99418eb84c423b262fd895a83d57ef6b4751e6ee88599f32" }, "model.language_model.layers.33.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b653e80d0c7fc4875cd35b35df6b1297b89f0923eab1de68657fb4cb9f7048ca", "shape": [ 17408, 5120 ], "source_sha256": "b653e80d0c7fc4875cd35b35df6b1297b89f0923eab1de68657fb4cb9f7048ca" }, "model.language_model.layers.33.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "11b54fb1bada27780adf1fda55cdb2e59e55ec6d334cc5023adf95c4bb71300b", "shape": [ 5120 ], "source_sha256": "11b54fb1bada27780adf1fda55cdb2e59e55ec6d334cc5023adf95c4bb71300b" }, "model.language_model.layers.34.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "d1d9d55c6e599a16814e489259bb8125fbabada60ed587fe50636e95b8b3b9cb", "shape": [ 5120 ], "source_sha256": "d1d9d55c6e599a16814e489259bb8125fbabada60ed587fe50636e95b8b3b9cb" }, "model.language_model.layers.34.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "fa0393645f611e1768153a37fa7c6541eb8ee2fba5328cd20d8913a4352865ff", "shape": [ 48 ], "source_sha256": "fa0393645f611e1768153a37fa7c6541eb8ee2fba5328cd20d8913a4352865ff" }, "model.language_model.layers.34.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "663a932cb3af20c34fa3f65e3717ac3877a16e3cd7c5e4be58288a043a616a62", "shape": [ 10240, 1, 4 ], "source_sha256": "663a932cb3af20c34fa3f65e3717ac3877a16e3cd7c5e4be58288a043a616a62" }, "model.language_model.layers.34.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "bc7883c777e8cf78e5e5d83da9923e98dadb99a6208620f71b5ada1407e5a1d1", "shape": [ 48 ], "source_sha256": "bc7883c777e8cf78e5e5d83da9923e98dadb99a6208620f71b5ada1407e5a1d1" }, "model.language_model.layers.34.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "a946bc0d3e143469330801b42810140de1a6c71695ca98a143c7e61d087419eb", "shape": [ 48, 5120 ], "source_sha256": "a946bc0d3e143469330801b42810140de1a6c71695ca98a143c7e61d087419eb" }, "model.language_model.layers.34.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "00551a4a7e4a6eb36d44346a2bb8e79337ddd4854250586959d1655b84aaeb80", "shape": [ 48, 5120 ], "source_sha256": "00551a4a7e4a6eb36d44346a2bb8e79337ddd4854250586959d1655b84aaeb80" }, "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "3e6da6cb77a10fb6ebb7102e65ff7a3bc6fa1365b5b6839de1f4e99030e6dd56", "shape": [ 10240, 5120 ], "source_sha256": "3e6da6cb77a10fb6ebb7102e65ff7a3bc6fa1365b5b6839de1f4e99030e6dd56" }, "model.language_model.layers.34.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "be1c7d30b42f9bc67e6c5a036cb5d6e742d971108851791ca631e2e0c44a2cb7", "shape": [ 6144, 5120 ], "source_sha256": "be1c7d30b42f9bc67e6c5a036cb5d6e742d971108851791ca631e2e0c44a2cb7" }, "model.language_model.layers.34.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "32ff821a03c1de5f961eea47158dd055b8293c348aa6d0c79d67f639074d6031", "shape": [ 128 ], "source_sha256": "32ff821a03c1de5f961eea47158dd055b8293c348aa6d0c79d67f639074d6031" }, "model.language_model.layers.34.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7e03b07c9ffa319db09746325478afda88964a312ec5efda7287b3fb01763f77", "shape": [ 5120, 6144 ], "source_sha256": "7e03b07c9ffa319db09746325478afda88964a312ec5efda7287b3fb01763f77" }, "model.language_model.layers.34.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "171162f045623d6e082c1cc009cead31c0942a7c4fe636c77215f4b50260faac", "shape": [ 5120, 17408 ], "source_sha256": "171162f045623d6e082c1cc009cead31c0942a7c4fe636c77215f4b50260faac" }, "model.language_model.layers.34.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "fc3708e03089b30290e28588aef087e313e20dd6c6dc49ab3fffc25a19ce3426", "shape": [ 17408, 5120 ], "source_sha256": "fc3708e03089b30290e28588aef087e313e20dd6c6dc49ab3fffc25a19ce3426" }, "model.language_model.layers.34.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "a35b7aff612ffca2e6173cb622b669926a614d707cf65f488cfaabbb17aada7b", "shape": [ 17408, 5120 ], "source_sha256": "a35b7aff612ffca2e6173cb622b669926a614d707cf65f488cfaabbb17aada7b" }, "model.language_model.layers.34.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a6b1a1b38228e959d933b3d1eff27929c6e365130762ac7b9736041606230b0e", "shape": [ 5120 ], "source_sha256": "a6b1a1b38228e959d933b3d1eff27929c6e365130762ac7b9736041606230b0e" }, "model.language_model.layers.35.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "b79a003ca47af7006a2d3c3b47ac4749aee0fb6f7caad29492d9b9d67f050c03", "shape": [ 5120 ], "source_sha256": "b79a003ca47af7006a2d3c3b47ac4749aee0fb6f7caad29492d9b9d67f050c03" }, "model.language_model.layers.35.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f6ebbe6015a6e097fc863b81af07eb05ef49ad3c48f1df695b156373d0c557f0", "shape": [ 5120, 17408 ], "source_sha256": "f6ebbe6015a6e097fc863b81af07eb05ef49ad3c48f1df695b156373d0c557f0" }, "model.language_model.layers.35.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "afbdaf1f3955627b571c8c0c71899e4ca4d0fe4a852f85e1e7eebf152a0ff375", "shape": [ 17408, 5120 ], "source_sha256": "afbdaf1f3955627b571c8c0c71899e4ca4d0fe4a852f85e1e7eebf152a0ff375" }, "model.language_model.layers.35.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "8949fa6fdad805d176819c12763bbfbf307165f3f7d0b41ed75c6ad6ad620422", "shape": [ 17408, 5120 ], "source_sha256": "8949fa6fdad805d176819c12763bbfbf307165f3f7d0b41ed75c6ad6ad620422" }, "model.language_model.layers.35.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "71bd56daffeab2ecbfd72766a677010a793d71d46855a730f24d902e98f7376f", "shape": [ 5120 ], "source_sha256": "71bd56daffeab2ecbfd72766a677010a793d71d46855a730f24d902e98f7376f" }, "model.language_model.layers.35.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "cc3baa1b2dd88a6b6d514a3296e898a0c92ed0eb2218f76c88bcdd9e42c440d0", "shape": [ 256 ], "source_sha256": "cc3baa1b2dd88a6b6d514a3296e898a0c92ed0eb2218f76c88bcdd9e42c440d0" }, "model.language_model.layers.35.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "fd2a2124fc4b72923fb0c6b325c1025f27bb350979415d29a2ca7384ade1e6de", "shape": [ 1024, 5120 ], "source_sha256": "fd2a2124fc4b72923fb0c6b325c1025f27bb350979415d29a2ca7384ade1e6de" }, "model.language_model.layers.35.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "ee4348c4a8949bfccca29b182c64a165df1812ebe06e4256e523c38ba834a844", "shape": [ 5120, 6144 ], "source_sha256": "ee4348c4a8949bfccca29b182c64a165df1812ebe06e4256e523c38ba834a844" }, "model.language_model.layers.35.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "38294eadc43d358b10dcbb57cac17d8c9a0756e53229f846c47c46cfab9689a0", "shape": [ 256 ], "source_sha256": "38294eadc43d358b10dcbb57cac17d8c9a0756e53229f846c47c46cfab9689a0" }, "model.language_model.layers.35.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "286b8b25a93d71f94578a0b5d718cf1631232a7d33ddf7ea5eab1bb6eb2f79f6", "shape": [ 12288, 5120 ], "source_sha256": "286b8b25a93d71f94578a0b5d718cf1631232a7d33ddf7ea5eab1bb6eb2f79f6" }, "model.language_model.layers.35.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "621412e49fce13f2105c587a8bcf576bdaad7795287afc81ed1485d814d7280c", "shape": [ 1024, 5120 ], "source_sha256": "621412e49fce13f2105c587a8bcf576bdaad7795287afc81ed1485d814d7280c" }, "model.language_model.layers.36.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "44d447678371b012e04bc9855485abd30eb3a90354c062ce58cf0f9e49d19d3e", "shape": [ 5120 ], "source_sha256": "44d447678371b012e04bc9855485abd30eb3a90354c062ce58cf0f9e49d19d3e" }, "model.language_model.layers.36.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "a845a876cba32174173b04b1c2c7cea2d2ce6d82e0d2f882203699689678bcce", "shape": [ 48 ], "source_sha256": "a845a876cba32174173b04b1c2c7cea2d2ce6d82e0d2f882203699689678bcce" }, "model.language_model.layers.36.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "da5067b2127cf261a4d375537e79a3babbb3c6885b42cb0a24ca6458f452f656", "shape": [ 10240, 1, 4 ], "source_sha256": "da5067b2127cf261a4d375537e79a3babbb3c6885b42cb0a24ca6458f452f656" }, "model.language_model.layers.36.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "4df588f937565e6f3997cd44821d11e8cdeafc058d338f7484ef3b91a6c803aa", "shape": [ 48 ], "source_sha256": "4df588f937565e6f3997cd44821d11e8cdeafc058d338f7484ef3b91a6c803aa" }, "model.language_model.layers.36.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "537b6a3e6da1a17a63cac839fdd5788afbf9231ff9d5ebf4e5888cccac2d6535", "shape": [ 48, 5120 ], "source_sha256": "537b6a3e6da1a17a63cac839fdd5788afbf9231ff9d5ebf4e5888cccac2d6535" }, "model.language_model.layers.36.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "f73c2fb187c8922edd1a21c956d75a0d3e723e9a47acefae72b80bd80def5907", "shape": [ 48, 5120 ], "source_sha256": "f73c2fb187c8922edd1a21c956d75a0d3e723e9a47acefae72b80bd80def5907" }, "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "22b5d1630b73bbb6c9b71225f59325f3177b557af7a2a94f6fab75818dcb510a", "shape": [ 10240, 5120 ], "source_sha256": "22b5d1630b73bbb6c9b71225f59325f3177b557af7a2a94f6fab75818dcb510a" }, "model.language_model.layers.36.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "883f12771dc6d2031ca3c39daa89f08d1c0ed4ae270a7e9e35e7db4268c0e65e", "shape": [ 6144, 5120 ], "source_sha256": "883f12771dc6d2031ca3c39daa89f08d1c0ed4ae270a7e9e35e7db4268c0e65e" }, "model.language_model.layers.36.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "f1dd0a3d76be1e50cd3c5d148bf4152f51061157eab9800123f50527c28362f8", "shape": [ 128 ], "source_sha256": "f1dd0a3d76be1e50cd3c5d148bf4152f51061157eab9800123f50527c28362f8" }, "model.language_model.layers.36.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "de36413eb25a3ea9d4e388f2061f9b1a9ec28d6d87cc04ffd293a0b174eb721a", "shape": [ 5120, 6144 ], "source_sha256": "de36413eb25a3ea9d4e388f2061f9b1a9ec28d6d87cc04ffd293a0b174eb721a" }, "model.language_model.layers.36.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "71ec4f96379ae578012d985f8c2289cb80569c2587692b2b64976b24c8ac63d0", "shape": [ 5120, 17408 ], "source_sha256": "71ec4f96379ae578012d985f8c2289cb80569c2587692b2b64976b24c8ac63d0" }, "model.language_model.layers.36.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "21e003ab4c5972e673931a52046d70ff283634da5a65de74075664451815c8db", "shape": [ 17408, 5120 ], "source_sha256": "21e003ab4c5972e673931a52046d70ff283634da5a65de74075664451815c8db" }, "model.language_model.layers.36.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "8ca8a40f4ec5ca542b653dfea7e47d3c03978179166f9a0924da1e8129d72481", "shape": [ 17408, 5120 ], "source_sha256": "8ca8a40f4ec5ca542b653dfea7e47d3c03978179166f9a0924da1e8129d72481" }, "model.language_model.layers.36.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a5fcb2551c5d7944ac7024a7dbaba945ed60a27a9fd8472e57ea0bd61fb34e46", "shape": [ 5120 ], "source_sha256": "a5fcb2551c5d7944ac7024a7dbaba945ed60a27a9fd8472e57ea0bd61fb34e46" }, "model.language_model.layers.37.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "51c83a3ce31b477eaa3eb28f64fb744674d706ad9184a2f81e1aae7e99346db9", "shape": [ 5120 ], "source_sha256": "51c83a3ce31b477eaa3eb28f64fb744674d706ad9184a2f81e1aae7e99346db9" }, "model.language_model.layers.37.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "7039e11c0c3a40b599357014fbbd1d012005cf3aa14231cd05d30bd2383f9703", "shape": [ 48 ], "source_sha256": "7039e11c0c3a40b599357014fbbd1d012005cf3aa14231cd05d30bd2383f9703" }, "model.language_model.layers.37.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "7adda9bbb7cc6ee90954aedb90eb24042c7c5cae6dde2d69682091f6b96f170f", "shape": [ 10240, 1, 4 ], "source_sha256": "7adda9bbb7cc6ee90954aedb90eb24042c7c5cae6dde2d69682091f6b96f170f" }, "model.language_model.layers.37.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "8cda820710204fda2de2447b40360e89b6a336243f21bbb2e658953c50d7e734", "shape": [ 48 ], "source_sha256": "8cda820710204fda2de2447b40360e89b6a336243f21bbb2e658953c50d7e734" }, "model.language_model.layers.37.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "f963593e24ffc3a051e83a9105e8a6d993e05e07dd48292f00e20826bb034a04", "shape": [ 48, 5120 ], "source_sha256": "f963593e24ffc3a051e83a9105e8a6d993e05e07dd48292f00e20826bb034a04" }, "model.language_model.layers.37.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "bf0e0526ab24cb04b520e2c000a3002a44906685e4a68f62c49af7112293f8f2", "shape": [ 48, 5120 ], "source_sha256": "bf0e0526ab24cb04b520e2c000a3002a44906685e4a68f62c49af7112293f8f2" }, "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "a74f8e3739701570ddc32ee41d817ee2df3ae03085a4ee5a65ee7682f8c4b14b", "shape": [ 10240, 5120 ], "source_sha256": "a74f8e3739701570ddc32ee41d817ee2df3ae03085a4ee5a65ee7682f8c4b14b" }, "model.language_model.layers.37.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "f512a048cfe259cbccbc2335cbba57eb62ceb975fe4ade1191f78bff04fe0fb7", "shape": [ 6144, 5120 ], "source_sha256": "f512a048cfe259cbccbc2335cbba57eb62ceb975fe4ade1191f78bff04fe0fb7" }, "model.language_model.layers.37.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "45938fc46aaa1522f95de1ec38542bd879f9511b30db4aa4105e6e298eda0e4c", "shape": [ 128 ], "source_sha256": "45938fc46aaa1522f95de1ec38542bd879f9511b30db4aa4105e6e298eda0e4c" } } }, { "bytes": 2108759408, "chunk_bytes": 16777216, "coalesced_source_segments": 7, "filename": "model-00011-of-00018.safetensors", "header_length": 3912, "header_sha256": "86816ce8a624f4aedb0a757c27cc0cd60df4d74d1dfcafeb138c7e77c6604f49", "schema_version": 1, "sha256": "6f5c889bbe7cdd98620257fdd4d74bd8c2c644c793ef565bf648a43e6367a178", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 128, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 30, "tensors": { "model.language_model.layers.37.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "2e73e784a8d276b30daa60463f11ab863aa80c2d4917b542bb4562d84af96263", "shape": [ 5120, 6144 ], "source_sha256": "2e73e784a8d276b30daa60463f11ab863aa80c2d4917b542bb4562d84af96263" }, "model.language_model.layers.37.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "bc30ec52cce10fabb27e8839a86c0d50e04b5cdf6a0f56f9c2e09b83318dda6b", "shape": [ 5120, 17408 ], "source_sha256": "bc30ec52cce10fabb27e8839a86c0d50e04b5cdf6a0f56f9c2e09b83318dda6b" }, "model.language_model.layers.37.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f1e201977471dd835a77b4a2686bc4335c5d815291b7bb56e48f8c9b83097247", "shape": [ 17408, 5120 ], "source_sha256": "f1e201977471dd835a77b4a2686bc4335c5d815291b7bb56e48f8c9b83097247" }, "model.language_model.layers.37.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "1d04ecaca00a7ac044a6e10a05d705b2d84980949c76671d350143c74f6ae707", "shape": [ 17408, 5120 ], "source_sha256": "1d04ecaca00a7ac044a6e10a05d705b2d84980949c76671d350143c74f6ae707" }, "model.language_model.layers.37.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ba6f3e385da87d13fc14d60696dd6b90ec47741e15e27fd7dcd385f58360a0ba", "shape": [ 5120 ], "source_sha256": "ba6f3e385da87d13fc14d60696dd6b90ec47741e15e27fd7dcd385f58360a0ba" }, "model.language_model.layers.38.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a776fe6a7471a80432ac524b281546a8cd09cbdb05e770205e20ced2b49496ed", "shape": [ 5120 ], "source_sha256": "a776fe6a7471a80432ac524b281546a8cd09cbdb05e770205e20ced2b49496ed" }, "model.language_model.layers.38.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "1580d9d93f18e2ee47be0408a9a92a09d7e4eaf7babd11f5cc5d37931b7ecd15", "shape": [ 48 ], "source_sha256": "1580d9d93f18e2ee47be0408a9a92a09d7e4eaf7babd11f5cc5d37931b7ecd15" }, "model.language_model.layers.38.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "4112e41c1e31e4e5954a10b6f9de0f4501351ed25af4f4db32b94cad70fa39c8", "shape": [ 10240, 1, 4 ], "source_sha256": "4112e41c1e31e4e5954a10b6f9de0f4501351ed25af4f4db32b94cad70fa39c8" }, "model.language_model.layers.38.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "dd697f77173d651984bfc1149ca32913b230db650e852ac71be166abfa5a62c6", "shape": [ 48 ], "source_sha256": "dd697f77173d651984bfc1149ca32913b230db650e852ac71be166abfa5a62c6" }, "model.language_model.layers.38.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "f9f4ad34ae894f30da6781d68dd515bba43308b573f98834d300fd354d339175", "shape": [ 48, 5120 ], "source_sha256": "f9f4ad34ae894f30da6781d68dd515bba43308b573f98834d300fd354d339175" }, "model.language_model.layers.38.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "2aab23989b028fdffb2016b00ab7bc428b44e50278280965b677e1d3aa46789f", "shape": [ 48, 5120 ], "source_sha256": "2aab23989b028fdffb2016b00ab7bc428b44e50278280965b677e1d3aa46789f" }, "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "266e321c277976970ed0dbcabccc6001a41ff3acadf389927d216cec0cf714cc", "shape": [ 10240, 5120 ], "source_sha256": "266e321c277976970ed0dbcabccc6001a41ff3acadf389927d216cec0cf714cc" }, "model.language_model.layers.38.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "2fb71dae8af1b74053060e2a96b0616c2e13f86cff5aa7286d1c1660795c2841", "shape": [ 6144, 5120 ], "source_sha256": "2fb71dae8af1b74053060e2a96b0616c2e13f86cff5aa7286d1c1660795c2841" }, "model.language_model.layers.38.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "0d8692719fb0d2c357856da79152a7aacf0c6d3d6279c533b7ee4bed2032c13e", "shape": [ 128 ], "source_sha256": "0d8692719fb0d2c357856da79152a7aacf0c6d3d6279c533b7ee4bed2032c13e" }, "model.language_model.layers.38.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "d376fdfc4c3c109e42481db3888fd6adaf328b8d17a77f85b4c60294499648ca", "shape": [ 5120, 6144 ], "source_sha256": "d376fdfc4c3c109e42481db3888fd6adaf328b8d17a77f85b4c60294499648ca" }, "model.language_model.layers.38.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "e4ef030d7b46fc9de0f01db77f312e9150269a52b16d937489930a41296e63fa", "shape": [ 5120, 17408 ], "source_sha256": "e4ef030d7b46fc9de0f01db77f312e9150269a52b16d937489930a41296e63fa" }, "model.language_model.layers.38.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "963472494287a7e70c86539c7c849b36c10d5934d1bb12b63cecc76c3587ad18", "shape": [ 17408, 5120 ], "source_sha256": "963472494287a7e70c86539c7c849b36c10d5934d1bb12b63cecc76c3587ad18" }, "model.language_model.layers.38.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ee1c63f54accf3e0196b13a69dc20a72228980d89c5aac70608bd38f9a0cb047", "shape": [ 17408, 5120 ], "source_sha256": "ee1c63f54accf3e0196b13a69dc20a72228980d89c5aac70608bd38f9a0cb047" }, "model.language_model.layers.38.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "9bd7fa54c2e9f270d8a22192d001afff2b03036a8dd98dad5b89f5afe22c8ee6", "shape": [ 5120 ], "source_sha256": "9bd7fa54c2e9f270d8a22192d001afff2b03036a8dd98dad5b89f5afe22c8ee6" }, "model.language_model.layers.39.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "381d1782dcc8acdb429fe74f689d219f88345eca48e53dcfd23b175d5888afe2", "shape": [ 5120 ], "source_sha256": "381d1782dcc8acdb429fe74f689d219f88345eca48e53dcfd23b175d5888afe2" }, "model.language_model.layers.39.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d71d933d6b9db0b77a881ac8eb71160bfecad55408c102b090a6190047dda103", "shape": [ 5120, 17408 ], "source_sha256": "d71d933d6b9db0b77a881ac8eb71160bfecad55408c102b090a6190047dda103" }, "model.language_model.layers.39.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "7eb35013fab34f0158199aec903884132bbadeb106304f20ffaa64d75b568d2f", "shape": [ 17408, 5120 ], "source_sha256": "7eb35013fab34f0158199aec903884132bbadeb106304f20ffaa64d75b568d2f" }, "model.language_model.layers.39.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "570054be8fd24ab5e922be3c17210b5bb860979fb0a3a193edc3645af0abf89d", "shape": [ 17408, 5120 ], "source_sha256": "570054be8fd24ab5e922be3c17210b5bb860979fb0a3a193edc3645af0abf89d" }, "model.language_model.layers.39.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "e349fd7cc9a27dc6e5d330a77bf44a77b899af122379320e67e9b448ceb6f3ec", "shape": [ 5120 ], "source_sha256": "e349fd7cc9a27dc6e5d330a77bf44a77b899af122379320e67e9b448ceb6f3ec" }, "model.language_model.layers.39.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "378862eb7a42ab8938f4c6f1e90ecff3e6d8430113404670a5c49f9082e279d2", "shape": [ 256 ], "source_sha256": "378862eb7a42ab8938f4c6f1e90ecff3e6d8430113404670a5c49f9082e279d2" }, "model.language_model.layers.39.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "571128841df6cae4dd03f148f7219076999ec64fcb7de2ddfad5fd0af624f0ae", "shape": [ 1024, 5120 ], "source_sha256": "571128841df6cae4dd03f148f7219076999ec64fcb7de2ddfad5fd0af624f0ae" }, "model.language_model.layers.39.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7166285871b603a8aa2188cb991f139eccf29ce6094af15b200eb4b2baaedf8a", "shape": [ 5120, 6144 ], "source_sha256": "7166285871b603a8aa2188cb991f139eccf29ce6094af15b200eb4b2baaedf8a" }, "model.language_model.layers.39.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "ee2afb6548b0f603afbdb539ad6011fa88ed74f776415ae9ef3c893899b5b28d", "shape": [ 256 ], "source_sha256": "ee2afb6548b0f603afbdb539ad6011fa88ed74f776415ae9ef3c893899b5b28d" }, "model.language_model.layers.39.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "9ddfbce92a17655f78a65ee154fc6a81b25414c5f9d2d8509edadf26819cfae9", "shape": [ 12288, 5120 ], "source_sha256": "9ddfbce92a17655f78a65ee154fc6a81b25414c5f9d2d8509edadf26819cfae9" }, "model.language_model.layers.39.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "2600782ba1be8ecf409c7802a8d97fb24c9bb737c147595a8cf7224b71abdff5", "shape": [ 1024, 5120 ], "source_sha256": "2600782ba1be8ecf409c7802a8d97fb24c9bb737c147595a8cf7224b71abdff5" } } }, { "bytes": 3979554136, "chunk_bytes": 16777216, "coalesced_source_segments": 13, "filename": "model-00012-of-00018.safetensors", "header_length": 9904, "header_sha256": "8b4ce997f33680f1070d2a16e5482201fce97e44fd1a10f05a24949806aa9920", "schema_version": 1, "sha256": "c99974af17d47aaa1f096d74fa4ceb1ebab0f30fcc4df11b2db1edf87fcd1668", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 242, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 76, "tensors": { "model.language_model.layers.40.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "fd2657bff2133785ef8e639d3e3c12e21b19b13a16dbe7e1b212d0ba1582dbf5", "shape": [ 5120 ], "source_sha256": "fd2657bff2133785ef8e639d3e3c12e21b19b13a16dbe7e1b212d0ba1582dbf5" }, "model.language_model.layers.40.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "c1d0099184437b5af2f379af20405357033d5e58a0a8fd3c1249d6e6ea7b89cd", "shape": [ 48 ], "source_sha256": "c1d0099184437b5af2f379af20405357033d5e58a0a8fd3c1249d6e6ea7b89cd" }, "model.language_model.layers.40.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "d70baf91314b64b99c4af19995e3232335ab4b55cb78eb6186d715328fb3aef2", "shape": [ 10240, 1, 4 ], "source_sha256": "d70baf91314b64b99c4af19995e3232335ab4b55cb78eb6186d715328fb3aef2" }, "model.language_model.layers.40.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "1fcc281311164cf6236b797b137b13587474af683d64a6fe068041f20937e4b0", "shape": [ 48 ], "source_sha256": "1fcc281311164cf6236b797b137b13587474af683d64a6fe068041f20937e4b0" }, "model.language_model.layers.40.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "40ff23fa86e9641411263c70d4379c3b3dbe84be0fef366d111d90a54ddba04c", "shape": [ 48, 5120 ], "source_sha256": "40ff23fa86e9641411263c70d4379c3b3dbe84be0fef366d111d90a54ddba04c" }, "model.language_model.layers.40.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "ff150d2d80ecf00c06e64b8b14b0c8eeb49cb67e1cc6287c8910aa2865b67bed", "shape": [ 48, 5120 ], "source_sha256": "ff150d2d80ecf00c06e64b8b14b0c8eeb49cb67e1cc6287c8910aa2865b67bed" }, "model.language_model.layers.40.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "6391ad605fbc140a401a91c5f01ee7798a60b02289a958f9d5c1d1100180f833", "shape": [ 10240, 5120 ], "source_sha256": "6391ad605fbc140a401a91c5f01ee7798a60b02289a958f9d5c1d1100180f833" }, "model.language_model.layers.40.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "21ecb796becd4ce1ecf6099cac70842784b26313184a8fdf3dbf4fed73765202", "shape": [ 6144, 5120 ], "source_sha256": "21ecb796becd4ce1ecf6099cac70842784b26313184a8fdf3dbf4fed73765202" }, "model.language_model.layers.40.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "bf8da981448c32d85cb29bce85a411a4195e639c67ff534449a97d9c61db715c", "shape": [ 128 ], "source_sha256": "bf8da981448c32d85cb29bce85a411a4195e639c67ff534449a97d9c61db715c" }, "model.language_model.layers.40.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "b01adb66421feb52346a9a84b3ebf67b13782b076c571a6336bb56acf85e95fd", "shape": [ 5120, 6144 ], "source_sha256": "b01adb66421feb52346a9a84b3ebf67b13782b076c571a6336bb56acf85e95fd" }, "model.language_model.layers.40.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "2d035b1e61882ecce1936d590537e0d18826c430df7e5739d832540123de7b5d", "shape": [ 5120, 17408 ], "source_sha256": "2d035b1e61882ecce1936d590537e0d18826c430df7e5739d832540123de7b5d" }, "model.language_model.layers.40.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b8ed48b8d941506293cd9aa224aa302643093f5360538be41fca928d3f847e0a", "shape": [ 17408, 5120 ], "source_sha256": "b8ed48b8d941506293cd9aa224aa302643093f5360538be41fca928d3f847e0a" }, "model.language_model.layers.40.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d9f7e3712cc9ff57cb9526796d8c31a41ba76f231f792f28edc301ac97df32d0", "shape": [ 17408, 5120 ], "source_sha256": "d9f7e3712cc9ff57cb9526796d8c31a41ba76f231f792f28edc301ac97df32d0" }, "model.language_model.layers.40.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "178a2e89fbcd9d356a5bedbc3029c7dc87b213c763946862cd70f6bae2cabab4", "shape": [ 5120 ], "source_sha256": "178a2e89fbcd9d356a5bedbc3029c7dc87b213c763946862cd70f6bae2cabab4" }, "model.language_model.layers.41.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "5b251cf1d620fcf16b4eca1d18d80cc4c1b3e8c9237e4deda7d0d83fd326373d", "shape": [ 5120 ], "source_sha256": "5b251cf1d620fcf16b4eca1d18d80cc4c1b3e8c9237e4deda7d0d83fd326373d" }, "model.language_model.layers.41.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "9c9f5be8b8747fcf026753af44737154755453639eb2901d2bd7a1cd27d96985", "shape": [ 48 ], "source_sha256": "9c9f5be8b8747fcf026753af44737154755453639eb2901d2bd7a1cd27d96985" }, "model.language_model.layers.41.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "14b9a086d8e0803db98b1f679334fd1f60666392ce6181c050fe408387de7101", "shape": [ 10240, 1, 4 ], "source_sha256": "14b9a086d8e0803db98b1f679334fd1f60666392ce6181c050fe408387de7101" }, "model.language_model.layers.41.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "36d167f951aa3215584ed93fa536317e12ea5e523cc37e68e6e05e56cf8fb607", "shape": [ 48 ], "source_sha256": "36d167f951aa3215584ed93fa536317e12ea5e523cc37e68e6e05e56cf8fb607" }, "model.language_model.layers.41.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "d6f92eddb1d65527fb3c07d92985b6be669820533406083ae843d5dd091ead1c", "shape": [ 48, 5120 ], "source_sha256": "d6f92eddb1d65527fb3c07d92985b6be669820533406083ae843d5dd091ead1c" }, "model.language_model.layers.41.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "161dbbf1a5fe89dc11d889cc34278edde37c1b622babfaa0df21cd8e931c45a8", "shape": [ 48, 5120 ], "source_sha256": "161dbbf1a5fe89dc11d889cc34278edde37c1b622babfaa0df21cd8e931c45a8" }, "model.language_model.layers.41.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "6983b7aeb1e338f2b24cd6b4041d0e28f9f8f7da3beaf5ffab5898c3f78c53fa", "shape": [ 10240, 5120 ], "source_sha256": "6983b7aeb1e338f2b24cd6b4041d0e28f9f8f7da3beaf5ffab5898c3f78c53fa" }, "model.language_model.layers.41.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "de6c3b133aa52610d2d49bd646b0cbc4401d97bb2eea036c71a6a1361bdba01b", "shape": [ 6144, 5120 ], "source_sha256": "de6c3b133aa52610d2d49bd646b0cbc4401d97bb2eea036c71a6a1361bdba01b" }, "model.language_model.layers.41.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "a8ab8200c331bfeba262ea361a17e85d1a517bb846fb1da7bae4349e93c18256", "shape": [ 128 ], "source_sha256": "a8ab8200c331bfeba262ea361a17e85d1a517bb846fb1da7bae4349e93c18256" }, "model.language_model.layers.41.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "2f56a032b0e417a2c2e5efe1c0b98d9d0a71e8bd3c56e530aa2e2ff3bb15ffcb", "shape": [ 5120, 6144 ], "source_sha256": "2f56a032b0e417a2c2e5efe1c0b98d9d0a71e8bd3c56e530aa2e2ff3bb15ffcb" }, "model.language_model.layers.41.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c51b40edd27081f02dc9e590a1f199cd48a5217657682a812aa857aa6fe71367", "shape": [ 5120, 17408 ], "source_sha256": "c51b40edd27081f02dc9e590a1f199cd48a5217657682a812aa857aa6fe71367" }, "model.language_model.layers.41.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f987432848f2b8441497633f334c4089303fb3a0beca7a7ee5510f6fad5d8308", "shape": [ 17408, 5120 ], "source_sha256": "f987432848f2b8441497633f334c4089303fb3a0beca7a7ee5510f6fad5d8308" }, "model.language_model.layers.41.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "6b2eb0b2e41c0b360b97805418969a7a6bdc16a67fe3a2b8431ec50986402bd6", "shape": [ 17408, 5120 ], "source_sha256": "6b2eb0b2e41c0b360b97805418969a7a6bdc16a67fe3a2b8431ec50986402bd6" }, "model.language_model.layers.41.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a81eace500766376323e9c3ca82ade6aed95acc22a78959e963397e57d288cb9", "shape": [ 5120 ], "source_sha256": "a81eace500766376323e9c3ca82ade6aed95acc22a78959e963397e57d288cb9" }, "model.language_model.layers.42.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "fc8614304d0eff2b88bd26299b46fb69187d6ad92e8dcb0fd25120d5d21936ca", "shape": [ 5120 ], "source_sha256": "fc8614304d0eff2b88bd26299b46fb69187d6ad92e8dcb0fd25120d5d21936ca" }, "model.language_model.layers.42.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "0b49353b3d225f1a91c15186b0f86dc0d7d86b8752a602e210784695702d649b", "shape": [ 48 ], "source_sha256": "0b49353b3d225f1a91c15186b0f86dc0d7d86b8752a602e210784695702d649b" }, "model.language_model.layers.42.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "73558550e798e2f2c42f2dbd194e3719145bea1fcffd1a876f1409995fce7c99", "shape": [ 10240, 1, 4 ], "source_sha256": "73558550e798e2f2c42f2dbd194e3719145bea1fcffd1a876f1409995fce7c99" }, "model.language_model.layers.42.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "6113d525938547e286b620ee07fd6f64ed99aa2fa80ba17989cd7cee70d3ba2c", "shape": [ 48 ], "source_sha256": "6113d525938547e286b620ee07fd6f64ed99aa2fa80ba17989cd7cee70d3ba2c" }, "model.language_model.layers.42.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "4c1ef6f1eb781ca58f90e7c5a5db272569be3cc375c7d6d6a0b408ac93a55122", "shape": [ 48, 5120 ], "source_sha256": "4c1ef6f1eb781ca58f90e7c5a5db272569be3cc375c7d6d6a0b408ac93a55122" }, "model.language_model.layers.42.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "61132bc3fa31f945fcd6f54cf44e857d23065ae587109cca62364193075cad1f", "shape": [ 48, 5120 ], "source_sha256": "61132bc3fa31f945fcd6f54cf44e857d23065ae587109cca62364193075cad1f" }, "model.language_model.layers.42.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "67f702dc4ce1686430097e100942bcf6224bab71f8e4b89a0ff134be942f7f4c", "shape": [ 10240, 5120 ], "source_sha256": "67f702dc4ce1686430097e100942bcf6224bab71f8e4b89a0ff134be942f7f4c" }, "model.language_model.layers.42.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "5d17fbd8b2dbf325dcc7bd30d8449b015a2af5e6701e884fc5fa71d767127b56", "shape": [ 6144, 5120 ], "source_sha256": "5d17fbd8b2dbf325dcc7bd30d8449b015a2af5e6701e884fc5fa71d767127b56" }, "model.language_model.layers.42.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "135043e610faf024ed981fa21130b52704345c83506493da8bf6b20bbaab1515", "shape": [ 128 ], "source_sha256": "135043e610faf024ed981fa21130b52704345c83506493da8bf6b20bbaab1515" }, "model.language_model.layers.42.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "6c4251ab19cf31c8c90d801c3a7bda9783f6c38e44006e0fae69af0fa46d11a4", "shape": [ 5120, 6144 ], "source_sha256": "6c4251ab19cf31c8c90d801c3a7bda9783f6c38e44006e0fae69af0fa46d11a4" }, "model.language_model.layers.42.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "781377be6f57a0cbb9c7f8c8d496602b7f30f72946626768d9effdf53a38f910", "shape": [ 5120, 17408 ], "source_sha256": "781377be6f57a0cbb9c7f8c8d496602b7f30f72946626768d9effdf53a38f910" }, "model.language_model.layers.42.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ab4e8e0465b49929c493008ebafe2c24a8c8a1f9f62381d452d938bedbd7d32a", "shape": [ 17408, 5120 ], "source_sha256": "ab4e8e0465b49929c493008ebafe2c24a8c8a1f9f62381d452d938bedbd7d32a" }, "model.language_model.layers.42.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "cf4bfc0d200df62f2072e8607a90440c76d6b5798e91d50f5081ddeb6faa6c07", "shape": [ 17408, 5120 ], "source_sha256": "cf4bfc0d200df62f2072e8607a90440c76d6b5798e91d50f5081ddeb6faa6c07" }, "model.language_model.layers.42.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "58cf3a6cf489f981cbb8c1ae3f331e8e540b6fcf4b107ca6a5a495c68732d928", "shape": [ 5120 ], "source_sha256": "58cf3a6cf489f981cbb8c1ae3f331e8e540b6fcf4b107ca6a5a495c68732d928" }, "model.language_model.layers.43.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "18bed1258bdb27ca7bc0662058f401a8dc56785cf0026bd3bcd6c357178a5fae", "shape": [ 5120 ], "source_sha256": "18bed1258bdb27ca7bc0662058f401a8dc56785cf0026bd3bcd6c357178a5fae" }, "model.language_model.layers.43.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "fe87e21082bb97ce4e25a0b166901082de615b16faba6e4778c2465de497d81e", "shape": [ 5120, 17408 ], "source_sha256": "fe87e21082bb97ce4e25a0b166901082de615b16faba6e4778c2465de497d81e" }, "model.language_model.layers.43.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "3004c649b996644c84f69ac65dc58bd09f8878c84027234227932441f0e170b8", "shape": [ 17408, 5120 ], "source_sha256": "3004c649b996644c84f69ac65dc58bd09f8878c84027234227932441f0e170b8" }, "model.language_model.layers.43.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "9128d8069262e800f9ec2d2b176ca0b1f433666acad33d6319bf580368f4109c", "shape": [ 17408, 5120 ], "source_sha256": "9128d8069262e800f9ec2d2b176ca0b1f433666acad33d6319bf580368f4109c" }, "model.language_model.layers.43.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "086efac3f7b155ed98637a8e6c8699fb9ec073c478489c76bfa4bff73055ea05", "shape": [ 5120 ], "source_sha256": "086efac3f7b155ed98637a8e6c8699fb9ec073c478489c76bfa4bff73055ea05" }, "model.language_model.layers.43.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "27a8d7d0f21510fc09f515e644e01bd46d895ca468f447421119b076d3779964", "shape": [ 256 ], "source_sha256": "27a8d7d0f21510fc09f515e644e01bd46d895ca468f447421119b076d3779964" }, "model.language_model.layers.43.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "faa5582ad64fe864d241e30c7b3a1f57f6bb9611ec720613005d64f7db01a502", "shape": [ 1024, 5120 ], "source_sha256": "faa5582ad64fe864d241e30c7b3a1f57f6bb9611ec720613005d64f7db01a502" }, "model.language_model.layers.43.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "6159e3e14ea5d489f7e6beaa1bc873214e106d8deaf2bbdd5f51577d13ea5011", "shape": [ 5120, 6144 ], "source_sha256": "6159e3e14ea5d489f7e6beaa1bc873214e106d8deaf2bbdd5f51577d13ea5011" }, "model.language_model.layers.43.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "88097e605c726e221d08f854e251147314441df58825e90ea604b51620b7e0f5", "shape": [ 256 ], "source_sha256": "88097e605c726e221d08f854e251147314441df58825e90ea604b51620b7e0f5" }, "model.language_model.layers.43.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "d6b258978e7dbd1358a1024db9a6a2c76d111010d9d6e5357817ae42c427ba92", "shape": [ 12288, 5120 ], "source_sha256": "d6b258978e7dbd1358a1024db9a6a2c76d111010d9d6e5357817ae42c427ba92" }, "model.language_model.layers.43.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "4b6b8a338438406935eb7854df9bcc3dae9203f9e11998097cd0d7cbfe58bc05", "shape": [ 1024, 5120 ], "source_sha256": "4b6b8a338438406935eb7854df9bcc3dae9203f9e11998097cd0d7cbfe58bc05" }, "model.language_model.layers.44.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "4161f3f2d3149bd4f5906947fa670d1d60366a63505132775720b36fba9e8f91", "shape": [ 5120 ], "source_sha256": "4161f3f2d3149bd4f5906947fa670d1d60366a63505132775720b36fba9e8f91" }, "model.language_model.layers.44.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "46feef085d0866a5a32a566ff98d980902288442c1e60d7d9e35852ccf6ce094", "shape": [ 48 ], "source_sha256": "46feef085d0866a5a32a566ff98d980902288442c1e60d7d9e35852ccf6ce094" }, "model.language_model.layers.44.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "c5a2cb7cec5868d332b079a3752d635ac83faa4ca2baa9072c13026e29487c86", "shape": [ 10240, 1, 4 ], "source_sha256": "c5a2cb7cec5868d332b079a3752d635ac83faa4ca2baa9072c13026e29487c86" }, "model.language_model.layers.44.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "0eb199fad808c35ad70c149fb0543c81c12139ab4804e8310dd88e77f2f7076c", "shape": [ 48 ], "source_sha256": "0eb199fad808c35ad70c149fb0543c81c12139ab4804e8310dd88e77f2f7076c" }, "model.language_model.layers.44.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "5587fc024b5fda2b3b1c6a6ac8d64bcce160a646ac0777d981ba3c52604174f4", "shape": [ 48, 5120 ], "source_sha256": "5587fc024b5fda2b3b1c6a6ac8d64bcce160a646ac0777d981ba3c52604174f4" }, "model.language_model.layers.44.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "eac672e974a345eee1ca75cd5c506227bf81ad59dda445f2d5198342bf844a50", "shape": [ 48, 5120 ], "source_sha256": "eac672e974a345eee1ca75cd5c506227bf81ad59dda445f2d5198342bf844a50" }, "model.language_model.layers.44.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "7e73c4cc96ec728d89afe81910529954c93d2e746f9076451918e5aa5f1cbb1d", "shape": [ 10240, 5120 ], "source_sha256": "7e73c4cc96ec728d89afe81910529954c93d2e746f9076451918e5aa5f1cbb1d" }, "model.language_model.layers.44.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "c135f9e05e8570fd43b2ba08ebdb234c7436b47c138142aa9f46082ee1ed956c", "shape": [ 6144, 5120 ], "source_sha256": "c135f9e05e8570fd43b2ba08ebdb234c7436b47c138142aa9f46082ee1ed956c" }, "model.language_model.layers.44.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "37cb47bea67879450d70741ff3d438e5e3337da70fd6d7c7d71ed9bcfa87801a", "shape": [ 128 ], "source_sha256": "37cb47bea67879450d70741ff3d438e5e3337da70fd6d7c7d71ed9bcfa87801a" }, "model.language_model.layers.44.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "5d4e1dde576d8b074303348e7ee2ac0eaa8e54fd7b964bf338deaf853a171127", "shape": [ 5120, 6144 ], "source_sha256": "5d4e1dde576d8b074303348e7ee2ac0eaa8e54fd7b964bf338deaf853a171127" }, "model.language_model.layers.44.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "e75c243eb31fb31488b2fced91c19fca69d0480c4c8903ab41d929d3917d9e2e", "shape": [ 5120, 17408 ], "source_sha256": "e75c243eb31fb31488b2fced91c19fca69d0480c4c8903ab41d929d3917d9e2e" }, "model.language_model.layers.44.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "bde53061c9e302fc1138953df442a4066f20100e8e7a6e1dd4233838ce48fadf", "shape": [ 17408, 5120 ], "source_sha256": "bde53061c9e302fc1138953df442a4066f20100e8e7a6e1dd4233838ce48fadf" }, "model.language_model.layers.44.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "4c33533dc1db5df9d8596e551503b39bf67ab0ae2d3e37ad3b346a57e693c763", "shape": [ 17408, 5120 ], "source_sha256": "4c33533dc1db5df9d8596e551503b39bf67ab0ae2d3e37ad3b346a57e693c763" }, "model.language_model.layers.44.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "bad6eb445ebd9a2991c38958eccd5426fbae61725ec0b54d7b1eba55040e8ba6", "shape": [ 5120 ], "source_sha256": "bad6eb445ebd9a2991c38958eccd5426fbae61725ec0b54d7b1eba55040e8ba6" }, "model.language_model.layers.45.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "c09ee35dc754d9baf42422508e520dcf4fc1d8521a91d60b8272c8e4e7e2d643", "shape": [ 5120 ], "source_sha256": "c09ee35dc754d9baf42422508e520dcf4fc1d8521a91d60b8272c8e4e7e2d643" }, "model.language_model.layers.45.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "ffaabff3c21081080bba0cd40ef0951e9d43a260ad697c49de7e7c84824174b1", "shape": [ 48 ], "source_sha256": "ffaabff3c21081080bba0cd40ef0951e9d43a260ad697c49de7e7c84824174b1" }, "model.language_model.layers.45.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "2e422d7525100cba1bb96410c606c07353402dfb3edb191d6897fb56977fc8e8", "shape": [ 10240, 1, 4 ], "source_sha256": "2e422d7525100cba1bb96410c606c07353402dfb3edb191d6897fb56977fc8e8" }, "model.language_model.layers.45.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "7e4113ba62152d71c01fab4963cb2dec51fb833bd9602c72d318bfdb8632ce71", "shape": [ 48 ], "source_sha256": "7e4113ba62152d71c01fab4963cb2dec51fb833bd9602c72d318bfdb8632ce71" }, "model.language_model.layers.45.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "842f811f09386fe9274465b3e05965c4e4127dbb2d90bfe33cf2fbd9ddc5f459", "shape": [ 48, 5120 ], "source_sha256": "842f811f09386fe9274465b3e05965c4e4127dbb2d90bfe33cf2fbd9ddc5f459" }, "model.language_model.layers.45.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "6640d717f692a3a3a7aa76abfdef4fea8384e03a7d4f172cc22074f9abbce255", "shape": [ 48, 5120 ], "source_sha256": "6640d717f692a3a3a7aa76abfdef4fea8384e03a7d4f172cc22074f9abbce255" }, "model.language_model.layers.45.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "786edd6628e6a86cbd9c271de5c569436385ff72b24246504b78b3f96733d7fb", "shape": [ 10240, 5120 ], "source_sha256": "786edd6628e6a86cbd9c271de5c569436385ff72b24246504b78b3f96733d7fb" }, "model.language_model.layers.45.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "9f6bc5cdf8ffd41abc98343ccd7ccd5ccc212dc84c994b0591c806b40eec610a", "shape": [ 6144, 5120 ], "source_sha256": "9f6bc5cdf8ffd41abc98343ccd7ccd5ccc212dc84c994b0591c806b40eec610a" }, "model.language_model.layers.45.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "35aadd70da3997948242ac8fb005d1e130cad89256688fe9b70ef5b22973d812", "shape": [ 128 ], "source_sha256": "35aadd70da3997948242ac8fb005d1e130cad89256688fe9b70ef5b22973d812" } } }, { "bytes": 2108759408, "chunk_bytes": 16777216, "coalesced_source_segments": 7, "filename": "model-00013-of-00018.safetensors", "header_length": 3912, "header_sha256": "4eb96399fc07950b6280d53bd14d8181fc49a2a3d2681aa6d2e2cf1db7077a78", "schema_version": 1, "sha256": "0f621a75043527dced82ec209b09312f42ed5ec25b7a1eee4442f69120e065d1", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 128, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 30, "tensors": { "model.language_model.layers.45.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "878b13f67cb16c85f86f8dff9aef2c698752c4b2eca0007d54b3034780a0d62f", "shape": [ 5120, 6144 ], "source_sha256": "878b13f67cb16c85f86f8dff9aef2c698752c4b2eca0007d54b3034780a0d62f" }, "model.language_model.layers.45.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d267a4b6cd08d4a23c6e7d7347a690d2901bf934b57319bb0de5b2840a855887", "shape": [ 5120, 17408 ], "source_sha256": "d267a4b6cd08d4a23c6e7d7347a690d2901bf934b57319bb0de5b2840a855887" }, "model.language_model.layers.45.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "8e5cfa7119028cec8ceecc254d36410584c04846167fdbeb6971e99de37950bb", "shape": [ 17408, 5120 ], "source_sha256": "8e5cfa7119028cec8ceecc254d36410584c04846167fdbeb6971e99de37950bb" }, "model.language_model.layers.45.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "04e309deae060b62091917803646a2cf71ba50bb7838dda560a811cd83c5bfb7", "shape": [ 17408, 5120 ], "source_sha256": "04e309deae060b62091917803646a2cf71ba50bb7838dda560a811cd83c5bfb7" }, "model.language_model.layers.45.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "c79ab5bb2c2772b72ffedf9c34360094c9e10726d9bcf503493b469756f96f3e", "shape": [ 5120 ], "source_sha256": "c79ab5bb2c2772b72ffedf9c34360094c9e10726d9bcf503493b469756f96f3e" }, "model.language_model.layers.46.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "5eecb03dc1dd0e7fea1ddec8969bee75d6916be81f324faa8dd4a7bf3e8a00f3", "shape": [ 5120 ], "source_sha256": "5eecb03dc1dd0e7fea1ddec8969bee75d6916be81f324faa8dd4a7bf3e8a00f3" }, "model.language_model.layers.46.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "d6311c5cf3a2fa36b21408f3d1b254de23a0bac8983cd7f2217e6b51b5c28c51", "shape": [ 48 ], "source_sha256": "d6311c5cf3a2fa36b21408f3d1b254de23a0bac8983cd7f2217e6b51b5c28c51" }, "model.language_model.layers.46.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "7ae4eaf36ab7fb2c76769b41fd4bb3f68b9e838d9775a4c56864abc436c4b7e2", "shape": [ 10240, 1, 4 ], "source_sha256": "7ae4eaf36ab7fb2c76769b41fd4bb3f68b9e838d9775a4c56864abc436c4b7e2" }, "model.language_model.layers.46.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "471d7b0f22e368ff1ad3c0645edee416eca648f1ef7a5fbbe83dd4e14de1cdcf", "shape": [ 48 ], "source_sha256": "471d7b0f22e368ff1ad3c0645edee416eca648f1ef7a5fbbe83dd4e14de1cdcf" }, "model.language_model.layers.46.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "572dfe7351c217b4626388ecfd0641433ac175a3adc7da3a1cd0d9dcfc9a27cc", "shape": [ 48, 5120 ], "source_sha256": "572dfe7351c217b4626388ecfd0641433ac175a3adc7da3a1cd0d9dcfc9a27cc" }, "model.language_model.layers.46.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "b8e93c050127b5dc6a4befe829e531c53b4a351f7399036d3c2c78cfb43a92e6", "shape": [ 48, 5120 ], "source_sha256": "b8e93c050127b5dc6a4befe829e531c53b4a351f7399036d3c2c78cfb43a92e6" }, "model.language_model.layers.46.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "6ff3f321d7d52468c908fca70adb0bc095b8ea4c1cab707c1381055835b30fcd", "shape": [ 10240, 5120 ], "source_sha256": "6ff3f321d7d52468c908fca70adb0bc095b8ea4c1cab707c1381055835b30fcd" }, "model.language_model.layers.46.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "0add087cfd5bbd131262c2cdd77150cc8be1fbc2b6dccdea3f4a59d6008962b8", "shape": [ 6144, 5120 ], "source_sha256": "0add087cfd5bbd131262c2cdd77150cc8be1fbc2b6dccdea3f4a59d6008962b8" }, "model.language_model.layers.46.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "968db6dd44b5b9787f19ba470dfd4729350bb7a5da5cd74d7ddb17c25c7bc839", "shape": [ 128 ], "source_sha256": "968db6dd44b5b9787f19ba470dfd4729350bb7a5da5cd74d7ddb17c25c7bc839" }, "model.language_model.layers.46.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "351e00bb84f3506c909117297af1ce68a81a8cfa2a6138c758971549b52b0f92", "shape": [ 5120, 6144 ], "source_sha256": "351e00bb84f3506c909117297af1ce68a81a8cfa2a6138c758971549b52b0f92" }, "model.language_model.layers.46.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "2b7eeb6ab1886e16ea1d7656fcd0d6c85c161b2b65a83a7555b6a8d6e3f52582", "shape": [ 5120, 17408 ], "source_sha256": "2b7eeb6ab1886e16ea1d7656fcd0d6c85c161b2b65a83a7555b6a8d6e3f52582" }, "model.language_model.layers.46.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b2f6306f960b1d89b5668cc4d5eb7b4940decb02a39be1d534c1a276a350d383", "shape": [ 17408, 5120 ], "source_sha256": "b2f6306f960b1d89b5668cc4d5eb7b4940decb02a39be1d534c1a276a350d383" }, "model.language_model.layers.46.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "2a8b9a88ab5824c84a5191d8adcdcbfcfb7b8cfa650f5ab219b6c2f689a51a74", "shape": [ 17408, 5120 ], "source_sha256": "2a8b9a88ab5824c84a5191d8adcdcbfcfb7b8cfa650f5ab219b6c2f689a51a74" }, "model.language_model.layers.46.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "44b388e5aebbbd94163002cb2c82ab2e1199d8b33254a6bcab1c5bed3244ca1f", "shape": [ 5120 ], "source_sha256": "44b388e5aebbbd94163002cb2c82ab2e1199d8b33254a6bcab1c5bed3244ca1f" }, "model.language_model.layers.47.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "94a570c73462b0be97f4950aba96be16cf27c377800c75b19af96deea1f73cc6", "shape": [ 5120 ], "source_sha256": "94a570c73462b0be97f4950aba96be16cf27c377800c75b19af96deea1f73cc6" }, "model.language_model.layers.47.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "90f005c2a639d600db8091e6f224352181cdc7944c91c65ee211af881c456511", "shape": [ 5120, 17408 ], "source_sha256": "90f005c2a639d600db8091e6f224352181cdc7944c91c65ee211af881c456511" }, "model.language_model.layers.47.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "5b82cb5709652eca659505f006f75bbfece9df9ebda528535500f0574371ebc9", "shape": [ 17408, 5120 ], "source_sha256": "5b82cb5709652eca659505f006f75bbfece9df9ebda528535500f0574371ebc9" }, "model.language_model.layers.47.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "bd7e5adc220a2a787ba5ed3a5c140a112e2b2a157ab35ce937c11d65c3950f64", "shape": [ 17408, 5120 ], "source_sha256": "bd7e5adc220a2a787ba5ed3a5c140a112e2b2a157ab35ce937c11d65c3950f64" }, "model.language_model.layers.47.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "11a55814b4b87fc5d4db4b32b6cf319b00adeac641ab05c63c0a0515cb349d58", "shape": [ 5120 ], "source_sha256": "11a55814b4b87fc5d4db4b32b6cf319b00adeac641ab05c63c0a0515cb349d58" }, "model.language_model.layers.47.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "5cc87ad87900570aa3aa1b949ea9556e72bbf87c43c70939e55dffe4c09f89d3", "shape": [ 256 ], "source_sha256": "5cc87ad87900570aa3aa1b949ea9556e72bbf87c43c70939e55dffe4c09f89d3" }, "model.language_model.layers.47.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "184805270d3c80f3b1feb8801a73052fe457181fee0b4c7f6bdb89c5421a65aa", "shape": [ 1024, 5120 ], "source_sha256": "184805270d3c80f3b1feb8801a73052fe457181fee0b4c7f6bdb89c5421a65aa" }, "model.language_model.layers.47.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "9542a99e0411345f373e71786b8a4b16f826ef6efed6c6e5ce3c6d02e459848b", "shape": [ 5120, 6144 ], "source_sha256": "9542a99e0411345f373e71786b8a4b16f826ef6efed6c6e5ce3c6d02e459848b" }, "model.language_model.layers.47.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "c414c1293ce4d88e0f189adc3baf802f58c89f5179dcc0b63591aeaea4b21495", "shape": [ 256 ], "source_sha256": "c414c1293ce4d88e0f189adc3baf802f58c89f5179dcc0b63591aeaea4b21495" }, "model.language_model.layers.47.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "d255b76d0abe73062ce8d44aef867a8de3ccf5cd18f0509093dfdc63a6423e24", "shape": [ 12288, 5120 ], "source_sha256": "d255b76d0abe73062ce8d44aef867a8de3ccf5cd18f0509093dfdc63a6423e24" }, "model.language_model.layers.47.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "b22a825eb8a7863694efd3495648e4847e173d4d55ab900012c994c20f1a45f3", "shape": [ 1024, 5120 ], "source_sha256": "b22a825eb8a7863694efd3495648e4847e173d4d55ab900012c994c20f1a45f3" } } }, { "bytes": 3979554136, "chunk_bytes": 16777216, "coalesced_source_segments": 14, "filename": "model-00014-of-00018.safetensors", "header_length": 9904, "header_sha256": "b4292ae694fa8c16cd08902838bc1d6cf12195b5e76c62459f4cda537fdfc0a5", "schema_version": 1, "sha256": "dc238ff43e8787d6072907bdad95eac369ef0eed55bc9d826d8218ed7ea4d175", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 243, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 76, "tensors": { "model.language_model.layers.48.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "705a59de3c7d5a6612a70499901c10be1c0c4d4153a8fdfd3b2245776f1ba290", "shape": [ 5120 ], "source_sha256": "705a59de3c7d5a6612a70499901c10be1c0c4d4153a8fdfd3b2245776f1ba290" }, "model.language_model.layers.48.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "17f3c3576a964eb7e363cc115e0d716ba76b7ef30cc2265e50908b1bf9c26cea", "shape": [ 48 ], "source_sha256": "17f3c3576a964eb7e363cc115e0d716ba76b7ef30cc2265e50908b1bf9c26cea" }, "model.language_model.layers.48.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "ca634df4a9075a80edbe12b3499428762632a0ca5e2b8403d74c8bcea89b673c", "shape": [ 10240, 1, 4 ], "source_sha256": "ca634df4a9075a80edbe12b3499428762632a0ca5e2b8403d74c8bcea89b673c" }, "model.language_model.layers.48.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "57def50fa1e113fa0bbe2d08677414060c5d0f328f967a6343c773d99bd27c29", "shape": [ 48 ], "source_sha256": "57def50fa1e113fa0bbe2d08677414060c5d0f328f967a6343c773d99bd27c29" }, "model.language_model.layers.48.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "170edcd900fae90f93e4110c6b7d04588d6c040e68f465338dbec68ab371a814", "shape": [ 48, 5120 ], "source_sha256": "170edcd900fae90f93e4110c6b7d04588d6c040e68f465338dbec68ab371a814" }, "model.language_model.layers.48.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "c8d3c4020d1e626d699189da18b2c7bf13d141f3579f0f6233825ecdccd7c648", "shape": [ 48, 5120 ], "source_sha256": "c8d3c4020d1e626d699189da18b2c7bf13d141f3579f0f6233825ecdccd7c648" }, "model.language_model.layers.48.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "1f2cd92f52e654c253488c8dc2e0b2485a9f9364110c76ea835a50899a4d834c", "shape": [ 10240, 5120 ], "source_sha256": "1f2cd92f52e654c253488c8dc2e0b2485a9f9364110c76ea835a50899a4d834c" }, "model.language_model.layers.48.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "a2a5eb21b27ff318bcb9bf4879d99afa082a5b2f10756bacc8df4ad961c03d99", "shape": [ 6144, 5120 ], "source_sha256": "a2a5eb21b27ff318bcb9bf4879d99afa082a5b2f10756bacc8df4ad961c03d99" }, "model.language_model.layers.48.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "4961dad7e95d4160158d2b830465a84d87282a60889e42d78c88459071870a0c", "shape": [ 128 ], "source_sha256": "4961dad7e95d4160158d2b830465a84d87282a60889e42d78c88459071870a0c" }, "model.language_model.layers.48.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "c44e7f07df9c463e3ce0bb184f2a5fd08dc91a6bb85242bc80b4f65b551dff5e", "shape": [ 5120, 6144 ], "source_sha256": "c44e7f07df9c463e3ce0bb184f2a5fd08dc91a6bb85242bc80b4f65b551dff5e" }, "model.language_model.layers.48.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ef57deb33d61201d573e1a568e0e0e5c08cc690d86b84460526fcb2b676e1595", "shape": [ 5120, 17408 ], "source_sha256": "ef57deb33d61201d573e1a568e0e0e5c08cc690d86b84460526fcb2b676e1595" }, "model.language_model.layers.48.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "e3cab1c85cc9d6714253a35d5ee9e2437afb9271fc2b10c8bac8711a044b823f", "shape": [ 17408, 5120 ], "source_sha256": "e3cab1c85cc9d6714253a35d5ee9e2437afb9271fc2b10c8bac8711a044b823f" }, "model.language_model.layers.48.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b09dfc15f566207f0434b57782da06b430edea4e51d2f037a6a4c4ee8418d8b8", "shape": [ 17408, 5120 ], "source_sha256": "b09dfc15f566207f0434b57782da06b430edea4e51d2f037a6a4c4ee8418d8b8" }, "model.language_model.layers.48.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "644c6cbb5c65281de05f0df9b7987d6d1559cd19a0f1b0c580b29768f6b05eea", "shape": [ 5120 ], "source_sha256": "644c6cbb5c65281de05f0df9b7987d6d1559cd19a0f1b0c580b29768f6b05eea" }, "model.language_model.layers.49.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "4750249cdf51677eceaf1d05b72565bbcd1ee33bb4b2672a804180663a20e1b3", "shape": [ 5120 ], "source_sha256": "4750249cdf51677eceaf1d05b72565bbcd1ee33bb4b2672a804180663a20e1b3" }, "model.language_model.layers.49.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "22c165e545fab5ec5679c05ed8ae979ddc03f53be7c4049d6c878d37f80c9bce", "shape": [ 48 ], "source_sha256": "22c165e545fab5ec5679c05ed8ae979ddc03f53be7c4049d6c878d37f80c9bce" }, "model.language_model.layers.49.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "e2f0daf6965280a543cc6bfdc72eca26230cd1c901c1fdd47714e27b7c5b5c1c", "shape": [ 10240, 1, 4 ], "source_sha256": "e2f0daf6965280a543cc6bfdc72eca26230cd1c901c1fdd47714e27b7c5b5c1c" }, "model.language_model.layers.49.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "a6a404be079adcc1f91633d1442b44caa111257fa7fe90342917cd6d070ed180", "shape": [ 48 ], "source_sha256": "a6a404be079adcc1f91633d1442b44caa111257fa7fe90342917cd6d070ed180" }, "model.language_model.layers.49.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "c6e2e5e46f293ee184e78eb1c6f79f39401ecead9093f81c947d23eed30abd8d", "shape": [ 48, 5120 ], "source_sha256": "c6e2e5e46f293ee184e78eb1c6f79f39401ecead9093f81c947d23eed30abd8d" }, "model.language_model.layers.49.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "3c0f825ef9feb0d027b0c3f02c79424679c608452e26c842350e11b5d4eb6605", "shape": [ 48, 5120 ], "source_sha256": "3c0f825ef9feb0d027b0c3f02c79424679c608452e26c842350e11b5d4eb6605" }, "model.language_model.layers.49.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "f035abca2ad28ea42e0f0b6b8827f2de58dcaa4e5f123152d49af098d1b076c5", "shape": [ 10240, 5120 ], "source_sha256": "f035abca2ad28ea42e0f0b6b8827f2de58dcaa4e5f123152d49af098d1b076c5" }, "model.language_model.layers.49.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "bb2916542c1759b89066aa8fad2af84c0b06fff52f7a814ed747ed1407ea2c16", "shape": [ 6144, 5120 ], "source_sha256": "bb2916542c1759b89066aa8fad2af84c0b06fff52f7a814ed747ed1407ea2c16" }, "model.language_model.layers.49.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "77a956b310b0814e061a0c8b5a2d8f6a3d6b9a7bb6768c3177cc944f7ff4856b", "shape": [ 128 ], "source_sha256": "77a956b310b0814e061a0c8b5a2d8f6a3d6b9a7bb6768c3177cc944f7ff4856b" }, "model.language_model.layers.49.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "b50e80d9133fc21272ab01d13c810456a1b5ddc1d5f19547a906f00f5855bf2e", "shape": [ 5120, 6144 ], "source_sha256": "b50e80d9133fc21272ab01d13c810456a1b5ddc1d5f19547a906f00f5855bf2e" }, "model.language_model.layers.49.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "0b4a3fccbf07ebc1f57c6bd73c5d59d954836c78c02cdc735400ff1a2ef92af2", "shape": [ 5120, 17408 ], "source_sha256": "0b4a3fccbf07ebc1f57c6bd73c5d59d954836c78c02cdc735400ff1a2ef92af2" }, "model.language_model.layers.49.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "73ee6688414f1746820d3b0e504887f28dd1433faeaa27e8372b530cfa06564d", "shape": [ 17408, 5120 ], "source_sha256": "73ee6688414f1746820d3b0e504887f28dd1433faeaa27e8372b530cfa06564d" }, "model.language_model.layers.49.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "906de46a58231bbf0999a156b394c1c7b104795aa67f4ad881ee277f2f4829f9", "shape": [ 17408, 5120 ], "source_sha256": "906de46a58231bbf0999a156b394c1c7b104795aa67f4ad881ee277f2f4829f9" }, "model.language_model.layers.49.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a0d37949f784ff07258ce108a3085937de282d452e0ef56a0ab6e3b18ef3770c", "shape": [ 5120 ], "source_sha256": "a0d37949f784ff07258ce108a3085937de282d452e0ef56a0ab6e3b18ef3770c" }, "model.language_model.layers.50.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "92fed7e543eaf8e27bca18955b276b3477a32572175d1c01a9e1f65f3c177362", "shape": [ 5120 ], "source_sha256": "92fed7e543eaf8e27bca18955b276b3477a32572175d1c01a9e1f65f3c177362" }, "model.language_model.layers.50.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "9ddb87ed5b08336dbc65c40ef844da1f9d779a534d7f4befdca2d007fbd6e32b", "shape": [ 48 ], "source_sha256": "9ddb87ed5b08336dbc65c40ef844da1f9d779a534d7f4befdca2d007fbd6e32b" }, "model.language_model.layers.50.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "9f95b1c4ff0675b5a7f7ffd427b52cc07556c5aa4ff62776bf5a6d695d8a717c", "shape": [ 10240, 1, 4 ], "source_sha256": "9f95b1c4ff0675b5a7f7ffd427b52cc07556c5aa4ff62776bf5a6d695d8a717c" }, "model.language_model.layers.50.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "2e5971985039f3e3c965cd2a66b070944bce3fc076b28e714788a966b64143a5", "shape": [ 48 ], "source_sha256": "2e5971985039f3e3c965cd2a66b070944bce3fc076b28e714788a966b64143a5" }, "model.language_model.layers.50.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "86f2a5454d420b0cd5814b657e51b897961f732e88cb4edefae247e53ae4eb93", "shape": [ 48, 5120 ], "source_sha256": "86f2a5454d420b0cd5814b657e51b897961f732e88cb4edefae247e53ae4eb93" }, "model.language_model.layers.50.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "be47945018ef47d2f94f30d6aa456fd090b539a67cfaf6537c1bae8a7fe68cc0", "shape": [ 48, 5120 ], "source_sha256": "be47945018ef47d2f94f30d6aa456fd090b539a67cfaf6537c1bae8a7fe68cc0" }, "model.language_model.layers.50.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "4addec2e75ffa8f422b608c4d05336b63c1a205a090327d955a3ec7d0b6465e1", "shape": [ 10240, 5120 ], "source_sha256": "4addec2e75ffa8f422b608c4d05336b63c1a205a090327d955a3ec7d0b6465e1" }, "model.language_model.layers.50.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7aad0a9e71386ede7ada73848e48a98a29bf743676f51afc29ee04c58810e0dc", "shape": [ 6144, 5120 ], "source_sha256": "7aad0a9e71386ede7ada73848e48a98a29bf743676f51afc29ee04c58810e0dc" }, "model.language_model.layers.50.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "b64d15217f1d3d29dd640cba66bb3653b8486533da59a6c0566cf9e0b4e6860f", "shape": [ 128 ], "source_sha256": "b64d15217f1d3d29dd640cba66bb3653b8486533da59a6c0566cf9e0b4e6860f" }, "model.language_model.layers.50.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "0349a6db90c03a04908d7a1582a725a9eb316e83806959f03df49a4c902ae802", "shape": [ 5120, 6144 ], "source_sha256": "0349a6db90c03a04908d7a1582a725a9eb316e83806959f03df49a4c902ae802" }, "model.language_model.layers.50.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ca89bd22f0c6191be9246ca1d80f2ba5427484c3b2758c10656d2e0fd90243b5", "shape": [ 5120, 17408 ], "source_sha256": "ca89bd22f0c6191be9246ca1d80f2ba5427484c3b2758c10656d2e0fd90243b5" }, "model.language_model.layers.50.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "feafe8494668eba557e022a183383268855fa56192bf8032decba52c6fbe6846", "shape": [ 17408, 5120 ], "source_sha256": "feafe8494668eba557e022a183383268855fa56192bf8032decba52c6fbe6846" }, "model.language_model.layers.50.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "afa386923036d90ef8058920b2ce150b266d65c8503458d8d898c4a67f783add", "shape": [ 17408, 5120 ], "source_sha256": "afa386923036d90ef8058920b2ce150b266d65c8503458d8d898c4a67f783add" }, "model.language_model.layers.50.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "12facb73cdc799f0ca0fdb582dd1840ab1b90ba5b27ef1ac23e150e96db26dfb", "shape": [ 5120 ], "source_sha256": "12facb73cdc799f0ca0fdb582dd1840ab1b90ba5b27ef1ac23e150e96db26dfb" }, "model.language_model.layers.51.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "d9e5b50d633adb17d9b8825c348cb5375c23e6ca97d6364e8e720dbf0c3a056b", "shape": [ 5120 ], "source_sha256": "d9e5b50d633adb17d9b8825c348cb5375c23e6ca97d6364e8e720dbf0c3a056b" }, "model.language_model.layers.51.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "6587170815f06934bd7bfb77dad431f10a8605040d50a9f75843e3b2c3749074", "shape": [ 5120, 17408 ], "source_sha256": "6587170815f06934bd7bfb77dad431f10a8605040d50a9f75843e3b2c3749074" }, "model.language_model.layers.51.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "87155cf808083e04e5a42b6654368039bb5e34831bcf49976da14f77f9f5b2cf", "shape": [ 17408, 5120 ], "source_sha256": "87155cf808083e04e5a42b6654368039bb5e34831bcf49976da14f77f9f5b2cf" }, "model.language_model.layers.51.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "cc392df3a74aedf3cf743d38d7d797baafe33b1ba0aa600d7478fb8fadc0463f", "shape": [ 17408, 5120 ], "source_sha256": "cc392df3a74aedf3cf743d38d7d797baafe33b1ba0aa600d7478fb8fadc0463f" }, "model.language_model.layers.51.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "b36b3ca468fe270ec73eae06ad8f4336fb9a36816b21cbbf0038a1e8fcf93ed5", "shape": [ 5120 ], "source_sha256": "b36b3ca468fe270ec73eae06ad8f4336fb9a36816b21cbbf0038a1e8fcf93ed5" }, "model.language_model.layers.51.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "56ed90a9fe1afa8a1a28d2039ba35718a0c20e4d17c70a59442e280909b99933", "shape": [ 256 ], "source_sha256": "56ed90a9fe1afa8a1a28d2039ba35718a0c20e4d17c70a59442e280909b99933" }, "model.language_model.layers.51.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "80b5ac6597af0c11fe67707af14a8e0122abd30d927656a5f010534769a011d9", "shape": [ 1024, 5120 ], "source_sha256": "80b5ac6597af0c11fe67707af14a8e0122abd30d927656a5f010534769a011d9" }, "model.language_model.layers.51.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "f6f062e1a89d060cd7c2d695834513ad2d7e36c145ff726ba627d5392684db64", "shape": [ 5120, 6144 ], "source_sha256": "f6f062e1a89d060cd7c2d695834513ad2d7e36c145ff726ba627d5392684db64" }, "model.language_model.layers.51.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "f6805a093cdd228fde37ebd61fdd5e5cda83ea1a5d142e58e0cce26260c09a41", "shape": [ 256 ], "source_sha256": "f6805a093cdd228fde37ebd61fdd5e5cda83ea1a5d142e58e0cce26260c09a41" }, "model.language_model.layers.51.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "db39040e104642e7f12669bd5873c9cd22d5d9749a404f972da0921595f938c0", "shape": [ 12288, 5120 ], "source_sha256": "db39040e104642e7f12669bd5873c9cd22d5d9749a404f972da0921595f938c0" }, "model.language_model.layers.51.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "2121af14658e1020cff4c44aa368c962ce08aeca10b6b2ed768623c3e78d9d8d", "shape": [ 1024, 5120 ], "source_sha256": "2121af14658e1020cff4c44aa368c962ce08aeca10b6b2ed768623c3e78d9d8d" }, "model.language_model.layers.52.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "5d5f30e6f83e9daa240f9f3b6fd487183315194603bd19a67d86c6dd2a0b15ce", "shape": [ 5120 ], "source_sha256": "5d5f30e6f83e9daa240f9f3b6fd487183315194603bd19a67d86c6dd2a0b15ce" }, "model.language_model.layers.52.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "21eaa6947b0d481eaa4417560fe2382bc1c847334d82fd9036f399fa9335743b", "shape": [ 48 ], "source_sha256": "21eaa6947b0d481eaa4417560fe2382bc1c847334d82fd9036f399fa9335743b" }, "model.language_model.layers.52.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "edd3c984f0aebc56acbbee8f026b169c5473a691868cd1d025dd599e68078207", "shape": [ 10240, 1, 4 ], "source_sha256": "edd3c984f0aebc56acbbee8f026b169c5473a691868cd1d025dd599e68078207" }, "model.language_model.layers.52.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "23b50cd9ee89ac56b3c3661dbee06d4da40e6068ddc2f5dd143cecfd658fc41f", "shape": [ 48 ], "source_sha256": "23b50cd9ee89ac56b3c3661dbee06d4da40e6068ddc2f5dd143cecfd658fc41f" }, "model.language_model.layers.52.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "4c179cc9e1c5335b34f895664101cd5fc790e68ec423c6c5bb5110d6ee259faf", "shape": [ 48, 5120 ], "source_sha256": "4c179cc9e1c5335b34f895664101cd5fc790e68ec423c6c5bb5110d6ee259faf" }, "model.language_model.layers.52.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "74f7470378c2ee9d18df948acc63ef7877f431582f68c1e02beaa0ea747705bf", "shape": [ 48, 5120 ], "source_sha256": "74f7470378c2ee9d18df948acc63ef7877f431582f68c1e02beaa0ea747705bf" }, "model.language_model.layers.52.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "8fb97bc8c6f9ede8edf4962409ed240d31948f714b6a00176198021ae763213d", "shape": [ 10240, 5120 ], "source_sha256": "8fb97bc8c6f9ede8edf4962409ed240d31948f714b6a00176198021ae763213d" }, "model.language_model.layers.52.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "e21ad5f3f2eefc61f71c2f2825a73a681ce80b0186c10580aac0ccbb25308468", "shape": [ 6144, 5120 ], "source_sha256": "e21ad5f3f2eefc61f71c2f2825a73a681ce80b0186c10580aac0ccbb25308468" }, "model.language_model.layers.52.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "ecda1abf568494f8b5e306b5f21cbcd816d910b6cb0d0f78aeb735333780e70c", "shape": [ 128 ], "source_sha256": "ecda1abf568494f8b5e306b5f21cbcd816d910b6cb0d0f78aeb735333780e70c" }, "model.language_model.layers.52.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "5b15d56ed65217700a9970bc9fbdf8c8833a3d1f3e496618d6ea3f496f323e85", "shape": [ 5120, 6144 ], "source_sha256": "5b15d56ed65217700a9970bc9fbdf8c8833a3d1f3e496618d6ea3f496f323e85" }, "model.language_model.layers.52.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "77d79513e0da1f48b0455e5434e0d33c85bd7884f5a132b3f55a178da0f594f1", "shape": [ 5120, 17408 ], "source_sha256": "77d79513e0da1f48b0455e5434e0d33c85bd7884f5a132b3f55a178da0f594f1" }, "model.language_model.layers.52.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "9a7f8a5e7ec4bca3ce7650eb992b00fa6cc23b8ff13290c1609f54f6b066c7d0", "shape": [ 17408, 5120 ], "source_sha256": "9a7f8a5e7ec4bca3ce7650eb992b00fa6cc23b8ff13290c1609f54f6b066c7d0" }, "model.language_model.layers.52.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "90d00112c8fb981e703ece5cca459c9ccf9a570f31fbf5f58f865c1dac4481c7", "shape": [ 17408, 5120 ], "source_sha256": "90d00112c8fb981e703ece5cca459c9ccf9a570f31fbf5f58f865c1dac4481c7" }, "model.language_model.layers.52.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "58546f560cf0a4236a9248931e604ca5880138baebfc8cff4c9cb9a1794980b6", "shape": [ 5120 ], "source_sha256": "58546f560cf0a4236a9248931e604ca5880138baebfc8cff4c9cb9a1794980b6" }, "model.language_model.layers.53.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "7ddbfc1e24d1c9466719f2ed9090855645a583c7d9c57468f14e3e30bc2391a3", "shape": [ 5120 ], "source_sha256": "7ddbfc1e24d1c9466719f2ed9090855645a583c7d9c57468f14e3e30bc2391a3" }, "model.language_model.layers.53.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "fe5f69cddccad2da94896b9150c8f7f191ff55d27504c0111aa4483d612fb4f6", "shape": [ 48 ], "source_sha256": "fe5f69cddccad2da94896b9150c8f7f191ff55d27504c0111aa4483d612fb4f6" }, "model.language_model.layers.53.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "7619d78bee702ef92b4f9ea9dae344b44a0e7b4b527915cf2ebae58dfe00649a", "shape": [ 10240, 1, 4 ], "source_sha256": "7619d78bee702ef92b4f9ea9dae344b44a0e7b4b527915cf2ebae58dfe00649a" }, "model.language_model.layers.53.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "c99787ba6c85024b137616e8571da4a1e6d3e0da29b8e284b337fa4331c4dfd9", "shape": [ 48 ], "source_sha256": "c99787ba6c85024b137616e8571da4a1e6d3e0da29b8e284b337fa4331c4dfd9" }, "model.language_model.layers.53.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "0cc26531f6e016a1a9dc234c2a4c5f5b5f04d1cbc11b7c4045f2481496f962ac", "shape": [ 48, 5120 ], "source_sha256": "0cc26531f6e016a1a9dc234c2a4c5f5b5f04d1cbc11b7c4045f2481496f962ac" }, "model.language_model.layers.53.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "fcf9bdc409b3de4bd90f4cb949b51f7363ef33e954a8254fbbfc5256961fd054", "shape": [ 48, 5120 ], "source_sha256": "fcf9bdc409b3de4bd90f4cb949b51f7363ef33e954a8254fbbfc5256961fd054" }, "model.language_model.layers.53.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "3acbf88b03d68d188ac323a7465029f55501efac22d9087dc2921d99319e1cc1", "shape": [ 10240, 5120 ], "source_sha256": "3acbf88b03d68d188ac323a7465029f55501efac22d9087dc2921d99319e1cc1" }, "model.language_model.layers.53.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "5ba9bbf86320c51a1bf7ff78b298b937ccc34ff36bc2de778d3b8397fa0d042a", "shape": [ 6144, 5120 ], "source_sha256": "5ba9bbf86320c51a1bf7ff78b298b937ccc34ff36bc2de778d3b8397fa0d042a" }, "model.language_model.layers.53.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "6c66ea4b2e95526a359d4091317884c3f9ac140f6d67b9355b64130a296f91c7", "shape": [ 128 ], "source_sha256": "6c66ea4b2e95526a359d4091317884c3f9ac140f6d67b9355b64130a296f91c7" } } }, { "bytes": 2108759408, "chunk_bytes": 16777216, "coalesced_source_segments": 7, "filename": "model-00015-of-00018.safetensors", "header_length": 3912, "header_sha256": "258ee47416b0f78b6ca7f0f1ed6cccabaa95828756e31ad50897c9cd3f8bc79d", "schema_version": 1, "sha256": "3e07c7be92a7284db6c2635dbddffc98c125aa797627d985083808c3aea43a27", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 128, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 30, "tensors": { "model.language_model.layers.53.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "c91a093576fbdc67aac96658db81172533c2fa3244b9cd1addeb950cf21c5d4a", "shape": [ 5120, 6144 ], "source_sha256": "c91a093576fbdc67aac96658db81172533c2fa3244b9cd1addeb950cf21c5d4a" }, "model.language_model.layers.53.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "fe649fe4440cbe10b3a650b044053df75a0a7e0ea650bb0c557aba8aed344931", "shape": [ 5120, 17408 ], "source_sha256": "fe649fe4440cbe10b3a650b044053df75a0a7e0ea650bb0c557aba8aed344931" }, "model.language_model.layers.53.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "8c4e78fe64fb11abf252196b50710af752e87e1123065bff095634588fc3ff89", "shape": [ 17408, 5120 ], "source_sha256": "8c4e78fe64fb11abf252196b50710af752e87e1123065bff095634588fc3ff89" }, "model.language_model.layers.53.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "31be4656a26696e5692a79d022df77884cbe41ac04ed840068a124854598c4ad", "shape": [ 17408, 5120 ], "source_sha256": "31be4656a26696e5692a79d022df77884cbe41ac04ed840068a124854598c4ad" }, "model.language_model.layers.53.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "40ebddc726695e2cc9a2f7d4f2ac9da3ec87ce80f1fef6020f3163c528e29c42", "shape": [ 5120 ], "source_sha256": "40ebddc726695e2cc9a2f7d4f2ac9da3ec87ce80f1fef6020f3163c528e29c42" }, "model.language_model.layers.54.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "1de4220894542a7e30c5b31d517c7bcdc1b33665cc711cf77a1e8ac35f62fc16", "shape": [ 5120 ], "source_sha256": "1de4220894542a7e30c5b31d517c7bcdc1b33665cc711cf77a1e8ac35f62fc16" }, "model.language_model.layers.54.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "8fd9728066fd745c766beceb88c6b17b9a54a7dd1400f01f185774716c67229e", "shape": [ 48 ], "source_sha256": "8fd9728066fd745c766beceb88c6b17b9a54a7dd1400f01f185774716c67229e" }, "model.language_model.layers.54.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "77eeb7311ab8c08fa0d34c7a6174866d5c557336c3acc38b6661ff99565a7cb6", "shape": [ 10240, 1, 4 ], "source_sha256": "77eeb7311ab8c08fa0d34c7a6174866d5c557336c3acc38b6661ff99565a7cb6" }, "model.language_model.layers.54.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "7fd77c8197fdb4ac8347ebdcfd287a14980d34f28a3ee408e93b055244e4bef6", "shape": [ 48 ], "source_sha256": "7fd77c8197fdb4ac8347ebdcfd287a14980d34f28a3ee408e93b055244e4bef6" }, "model.language_model.layers.54.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "9b09cc69071b32c6f23ef4c5f8ef0d86aa5239fadfc27553bf80caaba80f2334", "shape": [ 48, 5120 ], "source_sha256": "9b09cc69071b32c6f23ef4c5f8ef0d86aa5239fadfc27553bf80caaba80f2334" }, "model.language_model.layers.54.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "14bf174ef4323856b3b444a4f60874bef590c7626d1310862f9f28771c8b72f7", "shape": [ 48, 5120 ], "source_sha256": "14bf174ef4323856b3b444a4f60874bef590c7626d1310862f9f28771c8b72f7" }, "model.language_model.layers.54.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "71daa1a11dec8b8e4e5ff673ed4f112269fd6994c48877da51fd489912813a13", "shape": [ 10240, 5120 ], "source_sha256": "71daa1a11dec8b8e4e5ff673ed4f112269fd6994c48877da51fd489912813a13" }, "model.language_model.layers.54.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "9dab05b9314e7e9929c8911577e544dc25ff8c44584876294c8b8bb420a79373", "shape": [ 6144, 5120 ], "source_sha256": "9dab05b9314e7e9929c8911577e544dc25ff8c44584876294c8b8bb420a79373" }, "model.language_model.layers.54.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "45ccfc4ea87e1177b8eebf65f28f9eca470622cd5a0555d43bd8418bead42348", "shape": [ 128 ], "source_sha256": "45ccfc4ea87e1177b8eebf65f28f9eca470622cd5a0555d43bd8418bead42348" }, "model.language_model.layers.54.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7e195e8b775b0dfbfecdf48b1f5f3df5eb91c391f6092e1e62bab0528e023a54", "shape": [ 5120, 6144 ], "source_sha256": "7e195e8b775b0dfbfecdf48b1f5f3df5eb91c391f6092e1e62bab0528e023a54" }, "model.language_model.layers.54.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "13d6ad083337d1708f21bc3fa1fbdd4df19d36ccb0de4d8da89ba80bc77100c3", "shape": [ 5120, 17408 ], "source_sha256": "13d6ad083337d1708f21bc3fa1fbdd4df19d36ccb0de4d8da89ba80bc77100c3" }, "model.language_model.layers.54.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "469d6b71694ee269d28f2c4356c6da69c48960ad9bd1262d529664beec09beaf", "shape": [ 17408, 5120 ], "source_sha256": "469d6b71694ee269d28f2c4356c6da69c48960ad9bd1262d529664beec09beaf" }, "model.language_model.layers.54.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "0bc28537d9a2e0357f78a807e77432c7f7828b80685c50e9a7c09c5701eedca3", "shape": [ 17408, 5120 ], "source_sha256": "0bc28537d9a2e0357f78a807e77432c7f7828b80685c50e9a7c09c5701eedca3" }, "model.language_model.layers.54.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "237c497c59f350faab01f7a9fca1a3dfbc1faac6c80ba29e3ef612ac20a0d7d1", "shape": [ 5120 ], "source_sha256": "237c497c59f350faab01f7a9fca1a3dfbc1faac6c80ba29e3ef612ac20a0d7d1" }, "model.language_model.layers.55.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "35a0d0e1ef121b44e40176b1b74b3988bb26f1231b6de85f9a95258ed65b79f2", "shape": [ 5120 ], "source_sha256": "35a0d0e1ef121b44e40176b1b74b3988bb26f1231b6de85f9a95258ed65b79f2" }, "model.language_model.layers.55.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "564f659ef7621ef9c5733cd81a726ac5b8923660fa693b2ba19e0a18dd4b16e3", "shape": [ 5120, 17408 ], "source_sha256": "564f659ef7621ef9c5733cd81a726ac5b8923660fa693b2ba19e0a18dd4b16e3" }, "model.language_model.layers.55.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "de0382987d5c1ca46b93dcb115c3f133a48e398477e1d0bb7a332bc529b9c268", "shape": [ 17408, 5120 ], "source_sha256": "de0382987d5c1ca46b93dcb115c3f133a48e398477e1d0bb7a332bc529b9c268" }, "model.language_model.layers.55.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f2796e8a7b0be4ea50ac43f24fe9cecb31dacdda05fb45e0fcf11697f24a8c31", "shape": [ 17408, 5120 ], "source_sha256": "f2796e8a7b0be4ea50ac43f24fe9cecb31dacdda05fb45e0fcf11697f24a8c31" }, "model.language_model.layers.55.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "f489b6ff7635c07efb6ebd35f2ac55c1892e5cc275bcc1e57c205c51b3ac3901", "shape": [ 5120 ], "source_sha256": "f489b6ff7635c07efb6ebd35f2ac55c1892e5cc275bcc1e57c205c51b3ac3901" }, "model.language_model.layers.55.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "1df9114ee7c1cdd2870fb9edfda2b146434ab8989c6dacf05edf82830305e3f9", "shape": [ 256 ], "source_sha256": "1df9114ee7c1cdd2870fb9edfda2b146434ab8989c6dacf05edf82830305e3f9" }, "model.language_model.layers.55.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "9b145046c233b6864339ac00a2da88f928f6458551368262aa4f31f1745baa59", "shape": [ 1024, 5120 ], "source_sha256": "9b145046c233b6864339ac00a2da88f928f6458551368262aa4f31f1745baa59" }, "model.language_model.layers.55.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7abab4c6e97bc9a0a542dcf8e495a2f4aea0c3e2d801729676254b2f8972259d", "shape": [ 5120, 6144 ], "source_sha256": "7abab4c6e97bc9a0a542dcf8e495a2f4aea0c3e2d801729676254b2f8972259d" }, "model.language_model.layers.55.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "df675bc25f5f933e3f74912682917483f2b2c03e0ac9e93365a0bca604c5c753", "shape": [ 256 ], "source_sha256": "df675bc25f5f933e3f74912682917483f2b2c03e0ac9e93365a0bca604c5c753" }, "model.language_model.layers.55.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "772a382a2f1512a1f40c9c6991eb4731210f16ecf5c7ce7849d6ef2981125844", "shape": [ 12288, 5120 ], "source_sha256": "772a382a2f1512a1f40c9c6991eb4731210f16ecf5c7ce7849d6ef2981125844" }, "model.language_model.layers.55.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "f24325e8b41928d24bd33ead45d84c3a630cc078d6d947b84b9df14d4b25672a", "shape": [ 1024, 5120 ], "source_sha256": "f24325e8b41928d24bd33ead45d84c3a630cc078d6d947b84b9df14d4b25672a" } } }, { "bytes": 3979564472, "chunk_bytes": 16777216, "coalesced_source_segments": 15, "filename": "model-00016-of-00018.safetensors", "header_length": 10000, "header_sha256": "9e3431e652bbde50b547c656180135e2bc0c19e2430f51b9630765c4be9afbec", "schema_version": 1, "sha256": "6e499a617e78aec049c5859f091c10e16d4e3cf1190df8ac3ce9c02c16ecca50", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 244, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 77, "tensors": { "model.language_model.layers.56.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ed564a34ca785444f819e7ba8d669f82925dcf0a399ce825a7b476027665b8aa", "shape": [ 5120 ], "source_sha256": "ed564a34ca785444f819e7ba8d669f82925dcf0a399ce825a7b476027665b8aa" }, "model.language_model.layers.56.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "0c2606dec36c2b78acb99d642f8845aec4b8b3b6d55359296a0d175364df5534", "shape": [ 48 ], "source_sha256": "0c2606dec36c2b78acb99d642f8845aec4b8b3b6d55359296a0d175364df5534" }, "model.language_model.layers.56.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "1e5b76ce2086f3d3e49a38987246e67eb8009135e5ec97cdfac833cb7c03bad7", "shape": [ 10240, 1, 4 ], "source_sha256": "1e5b76ce2086f3d3e49a38987246e67eb8009135e5ec97cdfac833cb7c03bad7" }, "model.language_model.layers.56.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "ef9d58afaa5ca8afbe409fe4c1d85b39275ebefa55e68763ff73462ffd93d46c", "shape": [ 48 ], "source_sha256": "ef9d58afaa5ca8afbe409fe4c1d85b39275ebefa55e68763ff73462ffd93d46c" }, "model.language_model.layers.56.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "1290f6d38ff68a083666d0e4cf7cc50e1d13b4f2849500c103b2dd9ab2cceda9", "shape": [ 48, 5120 ], "source_sha256": "1290f6d38ff68a083666d0e4cf7cc50e1d13b4f2849500c103b2dd9ab2cceda9" }, "model.language_model.layers.56.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "bc35e2886fbd437fe84cf4a4ce34e899d60d3e084b30c2578faab6512b1d3a1d", "shape": [ 48, 5120 ], "source_sha256": "bc35e2886fbd437fe84cf4a4ce34e899d60d3e084b30c2578faab6512b1d3a1d" }, "model.language_model.layers.56.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "93b330bc803956b8dfa3ac9e33d35693698601947b08e9d29acd6a92f5c5669a", "shape": [ 10240, 5120 ], "source_sha256": "93b330bc803956b8dfa3ac9e33d35693698601947b08e9d29acd6a92f5c5669a" }, "model.language_model.layers.56.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "76e5cf9dd3869ad6bf738cf125ec7a6e079b15d6398d3775aa488340906ac1b7", "shape": [ 6144, 5120 ], "source_sha256": "76e5cf9dd3869ad6bf738cf125ec7a6e079b15d6398d3775aa488340906ac1b7" }, "model.language_model.layers.56.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "6c80ad37995ce9c96c2e6d4dfdf15c38764d98e0098a74f3abb612203b442f4a", "shape": [ 128 ], "source_sha256": "6c80ad37995ce9c96c2e6d4dfdf15c38764d98e0098a74f3abb612203b442f4a" }, "model.language_model.layers.56.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "0788aa5f8fcc871d9194184a53ea0a0cab0cc6427acf705f88c1d4a65e6bf5b6", "shape": [ 5120, 6144 ], "source_sha256": "0788aa5f8fcc871d9194184a53ea0a0cab0cc6427acf705f88c1d4a65e6bf5b6" }, "model.language_model.layers.56.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "27a381bbf44f1e2301b64485a6b93fb2a356fe951a26517ad2a0a5076f8d772c", "shape": [ 5120, 17408 ], "source_sha256": "27a381bbf44f1e2301b64485a6b93fb2a356fe951a26517ad2a0a5076f8d772c" }, "model.language_model.layers.56.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "6e923654b93aea6b86b446a22307c42e5b3e39cbd271833f2641fb4e0db6c3e8", "shape": [ 17408, 5120 ], "source_sha256": "6e923654b93aea6b86b446a22307c42e5b3e39cbd271833f2641fb4e0db6c3e8" }, "model.language_model.layers.56.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b76e1936417d29204d8622f9566504da833ec75d251c59a21260a9499c3e4d0d", "shape": [ 17408, 5120 ], "source_sha256": "b76e1936417d29204d8622f9566504da833ec75d251c59a21260a9499c3e4d0d" }, "model.language_model.layers.56.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a040b5113b245f2a2a712d262fff5b057f9368b6dc5cb484b656336d97f964ff", "shape": [ 5120 ], "source_sha256": "a040b5113b245f2a2a712d262fff5b057f9368b6dc5cb484b656336d97f964ff" }, "model.language_model.layers.57.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "ec45540bd26e6652a83f0fca499d98cd4bddb253569cc9d6798450fd0f9311d5", "shape": [ 5120 ], "source_sha256": "ec45540bd26e6652a83f0fca499d98cd4bddb253569cc9d6798450fd0f9311d5" }, "model.language_model.layers.57.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "c7a97c5db064515bb242408e7cf2f216da6a4afa51890b96189fd18993208bb2", "shape": [ 48 ], "source_sha256": "c7a97c5db064515bb242408e7cf2f216da6a4afa51890b96189fd18993208bb2" }, "model.language_model.layers.57.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "83889b6f6c72aa5a44110455a2f43cae14e0e89ebaaf97f36e324fc7b715f7ae", "shape": [ 10240, 1, 4 ], "source_sha256": "83889b6f6c72aa5a44110455a2f43cae14e0e89ebaaf97f36e324fc7b715f7ae" }, "model.language_model.layers.57.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "5fd0a092b9d9ee120d05989bc7ec3b755ca7f836947ad09bdcaa615a54f39662", "shape": [ 48 ], "source_sha256": "5fd0a092b9d9ee120d05989bc7ec3b755ca7f836947ad09bdcaa615a54f39662" }, "model.language_model.layers.57.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "5d1ec2b1826f5d02a6609b3e1826e16c9a816827ca69daedc5c2e922717c97be", "shape": [ 48, 5120 ], "source_sha256": "5d1ec2b1826f5d02a6609b3e1826e16c9a816827ca69daedc5c2e922717c97be" }, "model.language_model.layers.57.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "7f2658f204d7c1e228911beb287b3e9e0580b4af0d78ac41d5c969d2a32732ca", "shape": [ 48, 5120 ], "source_sha256": "7f2658f204d7c1e228911beb287b3e9e0580b4af0d78ac41d5c969d2a32732ca" }, "model.language_model.layers.57.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "7dbcc6013aad497766f3c91404a41ebf2614572ac55462530deb877be7841204", "shape": [ 10240, 5120 ], "source_sha256": "7dbcc6013aad497766f3c91404a41ebf2614572ac55462530deb877be7841204" }, "model.language_model.layers.57.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "b9b1d4ff43203623cd534fc64aa711fe6649f36d1833e023f1ef04c6261bcdaa", "shape": [ 6144, 5120 ], "source_sha256": "b9b1d4ff43203623cd534fc64aa711fe6649f36d1833e023f1ef04c6261bcdaa" }, "model.language_model.layers.57.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "d26ceb6b9b82cf91000fde0afd3cce55a3398b921f0ece22fded557bb13682fd", "shape": [ 128 ], "source_sha256": "d26ceb6b9b82cf91000fde0afd3cce55a3398b921f0ece22fded557bb13682fd" }, "model.language_model.layers.57.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "771e1e72614420399916c57fc8d43dd9f9b7ebaf4c4bd80f1909f1f8bef2116d", "shape": [ 5120, 6144 ], "source_sha256": "771e1e72614420399916c57fc8d43dd9f9b7ebaf4c4bd80f1909f1f8bef2116d" }, "model.language_model.layers.57.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b2b9826553eb1b0cdc81ec9b6959df782914719d32bb9759cd424842a0a4b00f", "shape": [ 5120, 17408 ], "source_sha256": "b2b9826553eb1b0cdc81ec9b6959df782914719d32bb9759cd424842a0a4b00f" }, "model.language_model.layers.57.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "fc8d3cd265612baf4a728a720bb2964be191a22b743ac4091c1b97cfc96b174f", "shape": [ 17408, 5120 ], "source_sha256": "fc8d3cd265612baf4a728a720bb2964be191a22b743ac4091c1b97cfc96b174f" }, "model.language_model.layers.57.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "31b4bf12c739114a220832dcc9e7721b7598d99cf08ae42bb251e6c554d06acd", "shape": [ 17408, 5120 ], "source_sha256": "31b4bf12c739114a220832dcc9e7721b7598d99cf08ae42bb251e6c554d06acd" }, "model.language_model.layers.57.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "f576ad049c1db5e119d1c2ab7d3bd91fd6ef3d24e53475cb61068f2a187764a2", "shape": [ 5120 ], "source_sha256": "f576ad049c1db5e119d1c2ab7d3bd91fd6ef3d24e53475cb61068f2a187764a2" }, "model.language_model.layers.58.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "8b2e25199f4942dc1cd1c2d6212b0a56aa03c030b9e5647dc11db2d9d1b11f17", "shape": [ 5120 ], "source_sha256": "8b2e25199f4942dc1cd1c2d6212b0a56aa03c030b9e5647dc11db2d9d1b11f17" }, "model.language_model.layers.58.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "6fcf690939695048174d3c43cdf1a06a2fe80558f399ab3ce01e0a22ff3b9d89", "shape": [ 48 ], "source_sha256": "6fcf690939695048174d3c43cdf1a06a2fe80558f399ab3ce01e0a22ff3b9d89" }, "model.language_model.layers.58.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "cf5ab0da940041fdaa85fd364bd0617122a88b1546435e3d282afb485aa5e59a", "shape": [ 10240, 1, 4 ], "source_sha256": "cf5ab0da940041fdaa85fd364bd0617122a88b1546435e3d282afb485aa5e59a" }, "model.language_model.layers.58.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "3383569505b675ec0b642bf0d60436245f19e846247cf681675ad09f1629b68e", "shape": [ 48 ], "source_sha256": "3383569505b675ec0b642bf0d60436245f19e846247cf681675ad09f1629b68e" }, "model.language_model.layers.58.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "b08ce3a81e9c9b1d931ffeeb8d2c3aab9bb14fd96c8019669d701f455ce6462d", "shape": [ 48, 5120 ], "source_sha256": "b08ce3a81e9c9b1d931ffeeb8d2c3aab9bb14fd96c8019669d701f455ce6462d" }, "model.language_model.layers.58.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "e51fe79ce9774b72d85dbf1a15f5b9235e684c674fd546c53277878bae229ecb", "shape": [ 48, 5120 ], "source_sha256": "e51fe79ce9774b72d85dbf1a15f5b9235e684c674fd546c53277878bae229ecb" }, "model.language_model.layers.58.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "4c0eaf7ed84dd11709562e7518349763b6eedf89be50a754701d6bf698931250", "shape": [ 10240, 5120 ], "source_sha256": "4c0eaf7ed84dd11709562e7518349763b6eedf89be50a754701d6bf698931250" }, "model.language_model.layers.58.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "c3cee3bc24ca9ce6102b6c866d0c14f312202de3c2d1a2f628de550aefcb0da4", "shape": [ 6144, 5120 ], "source_sha256": "c3cee3bc24ca9ce6102b6c866d0c14f312202de3c2d1a2f628de550aefcb0da4" }, "model.language_model.layers.58.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "a1a8c864340b70f48783a9607e799cd1e770d29d4fe929306047c16a3b52e359", "shape": [ 128 ], "source_sha256": "a1a8c864340b70f48783a9607e799cd1e770d29d4fe929306047c16a3b52e359" }, "model.language_model.layers.58.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "35c99cfe4f0141694373fee92453bd447338e894d35b508fecef10c68f4e1c39", "shape": [ 5120, 6144 ], "source_sha256": "35c99cfe4f0141694373fee92453bd447338e894d35b508fecef10c68f4e1c39" }, "model.language_model.layers.58.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "820355fb14d30ae45c60bb2a511f9e72bf3f8d7645d289772de7a2999b9999c7", "shape": [ 5120, 17408 ], "source_sha256": "820355fb14d30ae45c60bb2a511f9e72bf3f8d7645d289772de7a2999b9999c7" }, "model.language_model.layers.58.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "ed5af03049815f0bc2ee46101ea562c547ca27b2a7df908f8f9f21b97215699b", "shape": [ 17408, 5120 ], "source_sha256": "ed5af03049815f0bc2ee46101ea562c547ca27b2a7df908f8f9f21b97215699b" }, "model.language_model.layers.58.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "cde9e51167be5bcef03d5e8add73adad9d86933e6cd6eb163e17fdc12f33185a", "shape": [ 17408, 5120 ], "source_sha256": "cde9e51167be5bcef03d5e8add73adad9d86933e6cd6eb163e17fdc12f33185a" }, "model.language_model.layers.58.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "5a3331709d4dfd24c0993c7985358bb495d8cff1f8cea094a31a0990de13a9aa", "shape": [ 5120 ], "source_sha256": "5a3331709d4dfd24c0993c7985358bb495d8cff1f8cea094a31a0990de13a9aa" }, "model.language_model.layers.59.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "591d30fb728b2e349bd140e43b0a6d4cd7090332258c89b4a9ed36011df2759f", "shape": [ 5120 ], "source_sha256": "591d30fb728b2e349bd140e43b0a6d4cd7090332258c89b4a9ed36011df2759f" }, "model.language_model.layers.59.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b342d5f4417314368793235f7431b4da31fda3540b95dc51f927e60e7e0e56ac", "shape": [ 5120, 17408 ], "source_sha256": "b342d5f4417314368793235f7431b4da31fda3540b95dc51f927e60e7e0e56ac" }, "model.language_model.layers.59.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b421c853f7f7b40fec16d751fed338f25ecff8258d572d36ec743be315f66930", "shape": [ 17408, 5120 ], "source_sha256": "b421c853f7f7b40fec16d751fed338f25ecff8258d572d36ec743be315f66930" }, "model.language_model.layers.59.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "d27cb9001f22988073b0548258ba6d0c66075c9eabd63f7d3941d09b0219fa3f", "shape": [ 17408, 5120 ], "source_sha256": "d27cb9001f22988073b0548258ba6d0c66075c9eabd63f7d3941d09b0219fa3f" }, "model.language_model.layers.59.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "10931621c7e24523294c9e95d8915c96ebc4c123a6de3f01ec219a1bce8e4a26", "shape": [ 5120 ], "source_sha256": "10931621c7e24523294c9e95d8915c96ebc4c123a6de3f01ec219a1bce8e4a26" }, "model.language_model.layers.59.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "48ec9a59936e5f7501a74b3268b4c492612244f0291f5854efdb534958877e98", "shape": [ 256 ], "source_sha256": "48ec9a59936e5f7501a74b3268b4c492612244f0291f5854efdb534958877e98" }, "model.language_model.layers.59.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "ac9db90c2c37359ec33620a9f4e2c1697c2e997bc4bec40f3ea96e879738661a", "shape": [ 1024, 5120 ], "source_sha256": "ac9db90c2c37359ec33620a9f4e2c1697c2e997bc4bec40f3ea96e879738661a" }, "model.language_model.layers.59.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "be24625f52a6e687cdedfee21eec29c6103dfc93b38ada33d4390a803a7a5eff", "shape": [ 5120, 6144 ], "source_sha256": "be24625f52a6e687cdedfee21eec29c6103dfc93b38ada33d4390a803a7a5eff" }, "model.language_model.layers.59.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "b6c8e9668cbe09d342d32063630df2a7cd2f981574a26b7a2c70759bdf850d08", "shape": [ 256 ], "source_sha256": "b6c8e9668cbe09d342d32063630df2a7cd2f981574a26b7a2c70759bdf850d08" }, "model.language_model.layers.59.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "039e6c090fdb0cb38e416003c20e516d85927752f97e84240a2c4ca467454319", "shape": [ 12288, 5120 ], "source_sha256": "039e6c090fdb0cb38e416003c20e516d85927752f97e84240a2c4ca467454319" }, "model.language_model.layers.59.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "053f9fdda965753420200d69b15be7a268504baedbe23e1622f9ea63cbcdf27c", "shape": [ 1024, 5120 ], "source_sha256": "053f9fdda965753420200d69b15be7a268504baedbe23e1622f9ea63cbcdf27c" }, "model.language_model.layers.60.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "59827f319430ad9a48b7b4df6c65d5ad4276abbdd6f71c63df1addc1a206ff23", "shape": [ 5120 ], "source_sha256": "59827f319430ad9a48b7b4df6c65d5ad4276abbdd6f71c63df1addc1a206ff23" }, "model.language_model.layers.60.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "bb3f3811833400ae68e7bbbdb7e67b53def0b95d7df606ca1bed078ca6d6edd3", "shape": [ 48 ], "source_sha256": "bb3f3811833400ae68e7bbbdb7e67b53def0b95d7df606ca1bed078ca6d6edd3" }, "model.language_model.layers.60.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "ac1187cc1a0a9c3b9f377c8cf026aff07ca35224a17d222e6b1e7e9823002b64", "shape": [ 10240, 1, 4 ], "source_sha256": "ac1187cc1a0a9c3b9f377c8cf026aff07ca35224a17d222e6b1e7e9823002b64" }, "model.language_model.layers.60.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "2b300fd4e85a2864e020e6bbadde750d1318e1420a5befd427c9626076a98d0f", "shape": [ 48 ], "source_sha256": "2b300fd4e85a2864e020e6bbadde750d1318e1420a5befd427c9626076a98d0f" }, "model.language_model.layers.60.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "64e14b36dc827f989275b0cd287ca3f29695e9a9d2121de8df5b59e0931971ae", "shape": [ 48, 5120 ], "source_sha256": "64e14b36dc827f989275b0cd287ca3f29695e9a9d2121de8df5b59e0931971ae" }, "model.language_model.layers.60.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "6feac23097f136ae5e181c46babe3741e5445d832fd3298799b24cb47f61533c", "shape": [ 48, 5120 ], "source_sha256": "6feac23097f136ae5e181c46babe3741e5445d832fd3298799b24cb47f61533c" }, "model.language_model.layers.60.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "1ed5b91b3e81739db6b49d4953565c249f9028644060261f42f113b8f2da2876", "shape": [ 10240, 5120 ], "source_sha256": "1ed5b91b3e81739db6b49d4953565c249f9028644060261f42f113b8f2da2876" }, "model.language_model.layers.60.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "7fa265fe392230c1b312169f14e063c4938318acb4fb6013a663a930f5fd21b2", "shape": [ 6144, 5120 ], "source_sha256": "7fa265fe392230c1b312169f14e063c4938318acb4fb6013a663a930f5fd21b2" }, "model.language_model.layers.60.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "117fe5296db8514fd8df140445b0578762323fa3e8e1af6fb519b4e3798815d8", "shape": [ 128 ], "source_sha256": "117fe5296db8514fd8df140445b0578762323fa3e8e1af6fb519b4e3798815d8" }, "model.language_model.layers.60.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "16f4e255ec2ba682237bada6363e87d6b415bb5369fa31b30375271235e16181", "shape": [ 5120, 6144 ], "source_sha256": "16f4e255ec2ba682237bada6363e87d6b415bb5369fa31b30375271235e16181" }, "model.language_model.layers.60.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "0d07b7cada58f529fa7d76fef584bbe7e71f26ec1588cd68acca6163fd13eb90", "shape": [ 5120, 17408 ], "source_sha256": "0d07b7cada58f529fa7d76fef584bbe7e71f26ec1588cd68acca6163fd13eb90" }, "model.language_model.layers.60.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "4d560f0e7e16a846d0a901161e1d7fb2386c1dea1806d36d03ab114b79103373", "shape": [ 17408, 5120 ], "source_sha256": "4d560f0e7e16a846d0a901161e1d7fb2386c1dea1806d36d03ab114b79103373" }, "model.language_model.layers.60.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "0507cf1f83daebdc8751ad98240a047d1a21e48c91ef7d572e72c5729c155a81", "shape": [ 17408, 5120 ], "source_sha256": "0507cf1f83daebdc8751ad98240a047d1a21e48c91ef7d572e72c5729c155a81" }, "model.language_model.layers.60.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "f1c6f814c8bc64265e06fea1a808c16e511c8e760d8fb9f86768f38ead150665", "shape": [ 5120 ], "source_sha256": "f1c6f814c8bc64265e06fea1a808c16e511c8e760d8fb9f86768f38ead150665" }, "model.language_model.layers.61.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "a292296d5f7a31e63fa3472b661801c92c43c43692a8f662add2b5c6eb9247ad", "shape": [ 5120 ], "source_sha256": "a292296d5f7a31e63fa3472b661801c92c43c43692a8f662add2b5c6eb9247ad" }, "model.language_model.layers.61.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "57997bdf28d4e8cd2006f1bf1a9426027093bf9930c4df4a76206e5c000cec8b", "shape": [ 48 ], "source_sha256": "57997bdf28d4e8cd2006f1bf1a9426027093bf9930c4df4a76206e5c000cec8b" }, "model.language_model.layers.61.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "cba8266f72b364386949daab2de56317c9bfd6c2c0d516e7d1847e96404f4a9e", "shape": [ 10240, 1, 4 ], "source_sha256": "cba8266f72b364386949daab2de56317c9bfd6c2c0d516e7d1847e96404f4a9e" }, "model.language_model.layers.61.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "3740d42c834d0cc11a34fe2e9fe2c5dc3fb466b60ae5bc5a88be5ac00e75f133", "shape": [ 48 ], "source_sha256": "3740d42c834d0cc11a34fe2e9fe2c5dc3fb466b60ae5bc5a88be5ac00e75f133" }, "model.language_model.layers.61.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "731731d958f17c54c969a4e78d4f40c2c112e094d1fe095a3e3eb179772f2c27", "shape": [ 48, 5120 ], "source_sha256": "731731d958f17c54c969a4e78d4f40c2c112e094d1fe095a3e3eb179772f2c27" }, "model.language_model.layers.61.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "792904de4e3261dd5542de4ca51866f3354950e36bd52d0678f1504cbca26019", "shape": [ 48, 5120 ], "source_sha256": "792904de4e3261dd5542de4ca51866f3354950e36bd52d0678f1504cbca26019" }, "model.language_model.layers.61.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "71c7feb4014d65b2700b9da9ec77db2564ba664f1149fddfabec3f1f3a89e546", "shape": [ 10240, 5120 ], "source_sha256": "71c7feb4014d65b2700b9da9ec77db2564ba664f1149fddfabec3f1f3a89e546" }, "model.language_model.layers.61.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "84f9194892f785b322c58a9da8b36c0cb533d39ca2bbc3b48bb571aa5f4f1bf0", "shape": [ 6144, 5120 ], "source_sha256": "84f9194892f785b322c58a9da8b36c0cb533d39ca2bbc3b48bb571aa5f4f1bf0" }, "model.language_model.layers.61.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "349c8fb90b974951314169a26af43f45e125c9645286ec592004eb640f571d8c", "shape": [ 128 ], "source_sha256": "349c8fb90b974951314169a26af43f45e125c9645286ec592004eb640f571d8c" }, "model.language_model.norm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "d1d9fbdef187db987c117e021c7e4574ef32a5784c29f99d2722ce7654214738", "shape": [ 5120 ], "source_sha256": "d1d9fbdef187db987c117e021c7e4574ef32a5784c29f99d2722ce7654214738" } } }, { "bytes": 2108759408, "chunk_bytes": 16777216, "coalesced_source_segments": 7, "filename": "model-00017-of-00018.safetensors", "header_length": 3912, "header_sha256": "5b7e0cc1018e4abe496768eac00b7256e968ba1c5fa246f18d53558e355c6ad2", "schema_version": 1, "sha256": "e176bf3cdf4d62cd960662b91a594cf326c0ae5ceca4037657f1ba8a5117b2ae", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 128, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 30, "tensors": { "model.language_model.layers.61.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "d5acc7c47aa897d6ffc8b81515fc1d38ea8513bac2a048872f5139ecf2dddae4", "shape": [ 5120, 6144 ], "source_sha256": "d5acc7c47aa897d6ffc8b81515fc1d38ea8513bac2a048872f5139ecf2dddae4" }, "model.language_model.layers.61.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "dd84eb103e92d3beedf686376082252efd4098c2eb78c8e1c9d633976f4f30ea", "shape": [ 5120, 17408 ], "source_sha256": "dd84eb103e92d3beedf686376082252efd4098c2eb78c8e1c9d633976f4f30ea" }, "model.language_model.layers.61.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "c95efe23e3cc5753dea4ea5b94d986e5bb2f2e3c9f5008f6e6df1c53bffcdedc", "shape": [ 17408, 5120 ], "source_sha256": "c95efe23e3cc5753dea4ea5b94d986e5bb2f2e3c9f5008f6e6df1c53bffcdedc" }, "model.language_model.layers.61.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "8dc4dae086058ddfd589ebabef5a25649ad8f17c6955f467c45bfcbba29c21ed", "shape": [ 17408, 5120 ], "source_sha256": "8dc4dae086058ddfd589ebabef5a25649ad8f17c6955f467c45bfcbba29c21ed" }, "model.language_model.layers.61.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "c5f41cdca0bb4ae77430123f2a74dc0f4215b34acc35e4b11ee92543a089a3ae", "shape": [ 5120 ], "source_sha256": "c5f41cdca0bb4ae77430123f2a74dc0f4215b34acc35e4b11ee92543a089a3ae" }, "model.language_model.layers.62.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "d799ce8f899950193d287877fdadb1a01ea003860dc88922851147d3e46a7d1e", "shape": [ 5120 ], "source_sha256": "d799ce8f899950193d287877fdadb1a01ea003860dc88922851147d3e46a7d1e" }, "model.language_model.layers.62.linear_attn.A_log": { "bit_exact": true, "data_bytes": 192, "dtype": "F32", "output_sha256": "0abfdacaf0efee97b2bef3d888433f626847a8443aaf68a84896311dce4a52bb", "shape": [ 48 ], "source_sha256": "0abfdacaf0efee97b2bef3d888433f626847a8443aaf68a84896311dce4a52bb" }, "model.language_model.layers.62.linear_attn.conv1d.weight": { "bit_exact": true, "data_bytes": 81920, "dtype": "BF16", "output_sha256": "094e41ed4d028eeac8133cbe755a05d9ecaec2b14246ddd4ef074fa539a2e15f", "shape": [ 10240, 1, 4 ], "source_sha256": "094e41ed4d028eeac8133cbe755a05d9ecaec2b14246ddd4ef074fa539a2e15f" }, "model.language_model.layers.62.linear_attn.dt_bias": { "bit_exact": true, "data_bytes": 96, "dtype": "BF16", "output_sha256": "331de9353341f095922ced83351433eb6d802b81180ce579bb82e36b5cea2db8", "shape": [ 48 ], "source_sha256": "331de9353341f095922ced83351433eb6d802b81180ce579bb82e36b5cea2db8" }, "model.language_model.layers.62.linear_attn.in_proj_a.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "24facea12959e374d1216b1bd9ce61a9c136ff36411767ceddd9368e49fe0f86", "shape": [ 48, 5120 ], "source_sha256": "24facea12959e374d1216b1bd9ce61a9c136ff36411767ceddd9368e49fe0f86" }, "model.language_model.layers.62.linear_attn.in_proj_b.weight": { "bit_exact": true, "data_bytes": 491520, "dtype": "BF16", "output_sha256": "309e1f79c4d90143f7c74e135a1f795b36f3740757b03d694448c76d93dfe710", "shape": [ 48, 5120 ], "source_sha256": "309e1f79c4d90143f7c74e135a1f795b36f3740757b03d694448c76d93dfe710" }, "model.language_model.layers.62.linear_attn.in_proj_qkv.weight": { "bit_exact": true, "data_bytes": 104857600, "dtype": "BF16", "output_sha256": "905992a1416d73c111e4956ac8484c8b03927e5df4d80a5cc3c74744892eb7bd", "shape": [ 10240, 5120 ], "source_sha256": "905992a1416d73c111e4956ac8484c8b03927e5df4d80a5cc3c74744892eb7bd" }, "model.language_model.layers.62.linear_attn.in_proj_z.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "cfd9891ac3d7abd0a9a97bbf03d0c4b9580c0811a31e750ffc6fd0baa245f043", "shape": [ 6144, 5120 ], "source_sha256": "cfd9891ac3d7abd0a9a97bbf03d0c4b9580c0811a31e750ffc6fd0baa245f043" }, "model.language_model.layers.62.linear_attn.norm.weight": { "bit_exact": true, "data_bytes": 256, "dtype": "BF16", "output_sha256": "691ef76f9c84bed17620e0939b6a19999a3e87e7637762b6262cb91ee3f637aa", "shape": [ 128 ], "source_sha256": "691ef76f9c84bed17620e0939b6a19999a3e87e7637762b6262cb91ee3f637aa" }, "model.language_model.layers.62.linear_attn.out_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "a929d12d83c0a3328bf8cf3e04e19900cf4041459b5b456d2d7a853dcb52db72", "shape": [ 5120, 6144 ], "source_sha256": "a929d12d83c0a3328bf8cf3e04e19900cf4041459b5b456d2d7a853dcb52db72" }, "model.language_model.layers.62.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "b515a778b57340226f3b6a51f555c7669c2670597a06acc6b4561499e2372e65", "shape": [ 5120, 17408 ], "source_sha256": "b515a778b57340226f3b6a51f555c7669c2670597a06acc6b4561499e2372e65" }, "model.language_model.layers.62.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "f4869fa38e0ba4240969ef6f5094c62fd7946f6bdd3395d41001bab3c1b7cb2b", "shape": [ 17408, 5120 ], "source_sha256": "f4869fa38e0ba4240969ef6f5094c62fd7946f6bdd3395d41001bab3c1b7cb2b" }, "model.language_model.layers.62.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "e24c13432adbe5cadad76bc69335c50286779aa0e3c1af06ce0abf371e646fda", "shape": [ 17408, 5120 ], "source_sha256": "e24c13432adbe5cadad76bc69335c50286779aa0e3c1af06ce0abf371e646fda" }, "model.language_model.layers.62.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "23b11c235206a95da481d62d3bd09315aee705a80306125322af75c141139c66", "shape": [ 5120 ], "source_sha256": "23b11c235206a95da481d62d3bd09315aee705a80306125322af75c141139c66" }, "model.language_model.layers.63.input_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "696dcda8b7260f6934b537c66766075fdcbc0cb2f1e8c16153843829a209ef23", "shape": [ 5120 ], "source_sha256": "696dcda8b7260f6934b537c66766075fdcbc0cb2f1e8c16153843829a209ef23" }, "model.language_model.layers.63.mlp.down_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "aba83f4c62f3d95d26dbb8e9020cdfd3f97f61ac8217c4908394cc58cd5eca74", "shape": [ 5120, 17408 ], "source_sha256": "aba83f4c62f3d95d26dbb8e9020cdfd3f97f61ac8217c4908394cc58cd5eca74" }, "model.language_model.layers.63.mlp.gate_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "06e876687b875eeb0847b71ba546e241765d0c87188c57112b26f40c4b9bb11f", "shape": [ 17408, 5120 ], "source_sha256": "06e876687b875eeb0847b71ba546e241765d0c87188c57112b26f40c4b9bb11f" }, "model.language_model.layers.63.mlp.up_proj.weight": { "bit_exact": true, "data_bytes": 178257920, "dtype": "BF16", "output_sha256": "52204c727703e04f79a3d621833d86eeac7abe12870b21b7a846b86b043cc0c0", "shape": [ 17408, 5120 ], "source_sha256": "52204c727703e04f79a3d621833d86eeac7abe12870b21b7a846b86b043cc0c0" }, "model.language_model.layers.63.post_attention_layernorm.weight": { "bit_exact": true, "data_bytes": 10240, "dtype": "BF16", "output_sha256": "71401793f150a66cb40e0dc7be39615d6be245ae8a6636c5187dd2d41dd588a6", "shape": [ 5120 ], "source_sha256": "71401793f150a66cb40e0dc7be39615d6be245ae8a6636c5187dd2d41dd588a6" }, "model.language_model.layers.63.self_attn.k_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "956090c277d9eefa1d7fcaa55ebfa03ae0c0f3eed08a7cd667d28e6e3e5160a1", "shape": [ 256 ], "source_sha256": "956090c277d9eefa1d7fcaa55ebfa03ae0c0f3eed08a7cd667d28e6e3e5160a1" }, "model.language_model.layers.63.self_attn.k_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "4cc1f1ebb4eef7575279df23e7ca52943da6e78d000b19d2dd58230c15eb7f63", "shape": [ 1024, 5120 ], "source_sha256": "4cc1f1ebb4eef7575279df23e7ca52943da6e78d000b19d2dd58230c15eb7f63" }, "model.language_model.layers.63.self_attn.o_proj.weight": { "bit_exact": true, "data_bytes": 62914560, "dtype": "BF16", "output_sha256": "0543b4a01ed8af628fd2b6c12cc8fd06892d7cbe7e3754427fd977541b03f85d", "shape": [ 5120, 6144 ], "source_sha256": "0543b4a01ed8af628fd2b6c12cc8fd06892d7cbe7e3754427fd977541b03f85d" }, "model.language_model.layers.63.self_attn.q_norm.weight": { "bit_exact": true, "data_bytes": 512, "dtype": "BF16", "output_sha256": "a724704567558321f52e7057362a98c185857f6255bc507e3452275dc31f29f1", "shape": [ 256 ], "source_sha256": "a724704567558321f52e7057362a98c185857f6255bc507e3452275dc31f29f1" }, "model.language_model.layers.63.self_attn.q_proj.weight": { "bit_exact": true, "data_bytes": 125829120, "dtype": "BF16", "output_sha256": "3c7a955f7ab721be550b912cb1d310d2c1ffaa28d9802dfd05aa12c72f259855", "shape": [ 12288, 5120 ], "source_sha256": "3c7a955f7ab721be550b912cb1d310d2c1ffaa28d9802dfd05aa12c72f259855" }, "model.language_model.layers.63.self_attn.v_proj.weight": { "bit_exact": true, "data_bytes": 10485760, "dtype": "BF16", "output_sha256": "a97c03c00f4a83a997b0ef06bec93152dac299a025390984429b4d82011110d1", "shape": [ 1024, 5120 ], "source_sha256": "a97c03c00f4a83a997b0ef06bec93152dac299a025390984429b4d82011110d1" } } }, { "bytes": 2542796896, "chunk_bytes": 16777216, "coalesced_source_segments": 1, "filename": "model-00018-of-00018.safetensors", "header_length": 88, "header_sha256": "03bd5f1791ae04e53f5d728ecc0c7fa1ba680ea0d965251d7e9326acb9aa9a77", "schema_version": 1, "sha256": "2af195e3e76d5ab5bcf0e3e35a81c64899de5293f0efb7fd572d461b6422b509", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_range_read_calls": 152, "status": "verified-bit-exact", "target_index_sha256": "074240b04f2faf54810b8dbd889a3a8b6902695096066e6cf7627b88be6eb112", "tensor_count": 1, "tensors": { "lm_head.weight": { "bit_exact": true, "data_bytes": 2542796800, "dtype": "BF16", "output_sha256": "0c22b7d47912c0489eb25827c44949d641fa2731b4153fbd230f0f2022fa76f4", "shape": [ 248320, 5120 ], "source_sha256": "0c22b7d47912c0489eb25827c44949d641fa2731b4153fbd230f0f2022fa76f4" } } } ], "source_headers_sha256": "5e1a413f8de1f9dad07f0f3ab850ff292aa3c657af78349c43a1f2d7f2798cc5", "source_index_sha256": "170500500e4b2e0729a9d462fc55eb50d1d8a2e19bdce503a2a625aeb18a6929", "source_shard_count": 130, "status": "verified-bit-exact", "tensor_count": 851, "total_tensor_bytes": 53792001536 }, "verification_stage": "tensor-equivalence-verified-before-atomic-publication", "visibility": "private" }