{ "model": "/media/m2teamgroup/models/OneJev-9B-GGUF/OmniJev_OneJev-9B-bf16.gguf", "imatrix": "/media/m2teamgroup/models/OneJev-9B-GGUF/OmniJev_OneJev-9B-imatrix.gguf", "ftype": "IQ3_XS", "base_type": "iq3_s", "family": "iq", "recipe": "ident", "variant": "shr0.90", "auto_crush": false, "rung_mode": "share", "tier": "S", "rung_share": 0.9, "crush_pass_bytes": null, "embd_shares": { "output.weight": { "share": 0.1834, "type": "q4_k" }, "token_embd.weight": { "share": 0.0961, "type": "q4_k" } }, "arch": "hybrid", "tied": false, "n_layer": 32, "body_rule": true, "pins": { "^blk\\.0\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.0\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.1\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.1\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.2\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.2\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.4\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.4\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.5\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.5\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.6\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.6\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.8\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.8\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.9\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.9\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.10\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.10\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.12\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.12\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.13\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.13\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.14\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.14\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.16\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.16\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.17\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.17\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.18\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.18\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.20\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.20\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.21\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.21\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.22\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.22\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.24\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.24\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.25\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.25\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.26\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.26\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.28\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.28\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.29\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.29\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.30\\.ssm_alpha\\.weight$": "tiny: 131,072 params, kept at f32", "^blk\\.30\\.ssm_beta\\.weight$": "tiny: 131,072 params, kept at f32" }, "shape_pins": {}, "fixed_pins": { "blk.0.ssm_alpha.weight": "f32", "blk.0.ssm_beta.weight": "f32", "blk.1.ssm_alpha.weight": "f32", "blk.1.ssm_beta.weight": "f32", "blk.2.ssm_alpha.weight": "f32", "blk.2.ssm_beta.weight": "f32", "blk.4.ssm_alpha.weight": "f32", "blk.4.ssm_beta.weight": "f32", "blk.5.ssm_alpha.weight": "f32", "blk.5.ssm_beta.weight": "f32", "blk.6.ssm_alpha.weight": "f32", "blk.6.ssm_beta.weight": "f32", "blk.8.ssm_alpha.weight": "f32", "blk.8.ssm_beta.weight": "f32", "blk.9.ssm_alpha.weight": "f32", "blk.9.ssm_beta.weight": "f32", "blk.10.ssm_alpha.weight": "f32", "blk.10.ssm_beta.weight": "f32", "blk.12.ssm_alpha.weight": "f32", "blk.12.ssm_beta.weight": "f32", "blk.13.ssm_alpha.weight": "f32", "blk.13.ssm_beta.weight": "f32", "blk.14.ssm_alpha.weight": "f32", "blk.14.ssm_beta.weight": "f32", "blk.16.ssm_alpha.weight": "f32", "blk.16.ssm_beta.weight": "f32", "blk.17.ssm_alpha.weight": "f32", "blk.17.ssm_beta.weight": "f32", "blk.18.ssm_alpha.weight": "f32", "blk.18.ssm_beta.weight": "f32", "blk.20.ssm_alpha.weight": "f32", "blk.20.ssm_beta.weight": "f32", "blk.21.ssm_alpha.weight": "f32", "blk.21.ssm_beta.weight": "f32", "blk.22.ssm_alpha.weight": "f32", "blk.22.ssm_beta.weight": "f32", "blk.24.ssm_alpha.weight": "f32", "blk.24.ssm_beta.weight": "f32", "blk.25.ssm_alpha.weight": "f32", "blk.25.ssm_beta.weight": "f32", "blk.26.ssm_alpha.weight": "f32", "blk.26.ssm_beta.weight": "f32", "blk.28.ssm_alpha.weight": "f32", "blk.28.ssm_beta.weight": "f32", "blk.29.ssm_alpha.weight": "f32", "blk.29.ssm_beta.weight": "f32", "blk.30.ssm_alpha.weight": "f32", "blk.30.ssm_beta.weight": "f32" }, "embeddings": { "output.weight": "q4_k", "token_embd.weight": "q4_k" }, "bytes": { "heuristic_body+embd": 4520148992, "map_body+embd": 4227661824, "ratio": 0.9353, "note": "quantizable, unpinned tensors only; pinned/unquantized tensors are identical in both" }, "body_base_share": 0.9, "body_bpw": 3.569, "body_bpw_heuristic": 3.76, "total_params": 8953803264, "file_bytes_pred": 4257073152, "file_bpw_pred": 3.804, "histogram": { "attn_gate": { "iq3_s": 23, "q5_k": 1 }, "attn_k": { "q5_k": 7, "q4_k": 1 }, "attn_output": { "q5_k": 8 }, "attn_q": { "iq3_s": 8 }, "attn_qkv": { "iq3_s": 23, "q5_k": 1 }, "attn_v": { "q5_k": 6, "q6_k": 2 }, "ffn_down": { "iq3_s": 31, "q5_k": 1 }, "ffn_gate": { "iq3_s": 32 }, "ffn_up": { "iq3_s": 31, "q5_k": 1 }, "ssm_out": { "iq3_s": 18, "q4_k": 3, "q5_k": 2, "q6_k": 1 } }, "prior": "layout/prior.json", "pin_rule": "floor", "embd_cap": "heur", "generator": "auto_quant_v2.layout", "generator_key": "3bf8b43e20a68f0b", "quant_type": "IQ3_XS", "quantize_ftype": "IQ3_XS", "llama_cpp_version": "b11259", "commit": "24687c01f2f1e36eca618e35f7d5b4fc3ddd4dc2" }