Commit History
-
FP8 quantization: drop stale KD note, refresh PTQ metrics table
All variants are PTQ (no KD); refresh the FP8-vs-fp16 table on 1000 held-out clips measured against the regenerated PTQ packages.55c9d20
-
Add FP8 vs fp16 evaluation results (1000 samples) to README
411962a -
Update README: document FP8 quantization, remove usage/versions
71f19ca -
Remove legacy pytorch_model.bin and modeling_gigaam.py from main
a7f346b
-
Adding `safetensors` variant of this model (#1)
- Adding `safetensors` variant of this model (08e541077f1bfcaa49771772ab9e4f06721da714) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>fbf69cd -
Duplicate from ai-sage/GigaAM-v3
Co-authored-by: Aleksandr Kutsakov <Alexander4127@users.noreply.huggingface.co>7c307d9