| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| logs | 3 items | ||
| README.md | 1.94 kB xet | 28391cb4 | |
| SHA256SUMS | 479 Bytes xet | 9dc49b7b | |
| archive | 11.9 MB xet | e445246f | |
| decompressor.zip | 2.26 MB xet | 1ff40cf2 |
fx2-ft48-q256-b7-os-r5 (potatoheadjones)
14145194 B = archive 11883298 + decompressor.zip 2261896. Method: fx2-cmix-transformer (floating-bear's enwik8 port of upstream 83f2603)
with the transformer weights replaced by checkpoint models/ft48-q256-b7-6m-q4-fp32.tch (7 quantization levels); decoder-only bundle (FX2_DECODER_ONLY, pack_bundle.py --decoder).
| file | bytes | sha256 |
|---|---|---|
| archive | 11883298 | ed07695c9969da7b8bd0ef96fd456f1f2e4b9349cb9ea3d6757619a5d0ea8346 |
| decompressor.zip | 2261896 | 1a80df38e0b3163beeb1df06926fd43f2905ff567dd0a15421a758e1829d1e31 |
Decode: unzip decompressor.zip -d dec && python3 dec/d archive enwik8.out on Ubuntu 24.04 (glibc 2.39), x86-64-v3, one core, ~6 GB RAM.
Build: clang-17/lld-17, PGO=0 UPX=0 ./build_and_construct_comp.sh, -march=x86-64-v3 -mrecip=none; AVX2-only and no-reciprocal checks passed.
Build-time cmix knobs (scripts/fx2_knobs.py; stock = 923/3000/0.03/1.0): SEED=923 UPDATE_LIMIT=3000 FX2_LSTM_LR=0.03 FX2_MIX_LR_SCALE=1.0. MIXER CLAMP: mixer-input probability clamp FX2_MIX_CLAMP=1.0e-5 instead of stock 1.0e-4 (swagged-out-bot's measurement; encoder and decoder share it). WEIGHT CODING: the weights member is re-coded with swagged-out-bot's ENC_INT3 (3-bit width-matched tree + count-adaptive rate, cap 7; their result 20260919-191036-788) and the decoder carries their loader patch; credit for that saving: swagged-out-bot. SIDE TENSORS: the float32 side tensors (convolutions, gates, biases) are rounded to 5 mantissa bits before coding (scripts/fx2_round_f32.py); still float32 on disk, decoder unchanged. OPT LEVEL: built with FX2_OPT=-Os for the model code and the transformer objects (encoder and decoder share it; a -O3 build cannot decode this archive).
Round trip: see logs/verify.log (tools/verify_bundle.sh, fresh directory, cmp vs canonical enwik8).
Transformer loss during compression: 1.176751 nats/token (full stream).
- Total size
- 515 MB
- Files
- 257
- Last updated
- Nov 2
- Pre-warmed CDN
- US EU US EU