Views
No views yet
ebb281ec70b05090aa6165b016eac8ec08e71b17 (upstream Hugging Face commit; the shared local source directory is flattened).| Component | Method | Weight format | Targets |
|---|---|---|---|
| Decoder Linear layers | AutoRound | symmetric INT4, G256 | 252 |
lm_head | GPTQ | symmetric INT4, G256, static act-order | 1 |
| Vision encoder and merger Linear layers | GPTQ | symmetric INT8, per-channel, static act-order | 104 |
| Projectors / exceptions | — | No AutoRound target | See recipe.yaml |
NeelNanda/pile-10k text calibration (dataset
revision not captured; 512 samples, sequence length 1024, AutoRound 200
iterations, batch size 1). Stage 2 uses deterministic lmms-lab/flickr30k
(dataset revision not captured), test[:512], for 512 image-text samples
(sequence length 2048, batch size 1) used by the head and vision GPTQ stages.| Checkpoint | MMStar overall accuracy | Status |
|---|---|---|
| Source | 36.0667% | Matched full run, 2026-07-17 (T20260717-105421; exact-match local judge) |
| Existing GPTQ decoder baseline | 29.5333% | Matched full run, 2026-07-17 (T20260717-114055; exact-match local judge; 0/1500 inference and judge failures) |
| This hybrid checkpoint | 39.4667% | Matched full run, 2026-07-17; exact-match local judge; 0/1500 inference and judge failures |
EleutherAI/wikitext_document_level, wikitext-2-raw-v1, no example limit; 2026-07-18): source 14.6065; this checkpoint 15.9454; absolute degradation +1.3389; relative degradation +9.17%. Raw JSON evidence: perplexity_results/vlm_full_wikitext/qwen3_vl_4b_{source,autoround_w4g256_headgptq_w4_visiongptq_w8}_v3.json.python quantize.py --model-path /path/to/source-model --output-dir /path/to/new-outputquantize.py, recipe.yaml, and versions.txt.versions.txt.