Commit History
-
Add/update the quantized ONNX model files and README.md for Transformers.js v3
Verified signature## Applied Quantizations ### ✅ Based on `decoder_model_merged.onnx` *with* slimming ↳ ✅ `fp16`: `decoder_model_merged_fp16.onnx` (replaced because it was invalid) ↳ ✅ `int8`: `decoder_model_merged_int8.onnx` (added) ↳ ✅ `uint8`: `decoder_model_merged_uint8.onnx` (added) ↳ ✅ `q4`: `decoder_model_merged_q4.onnx` (added) ↳ ✅ `q4f16`: `decoder_model_merged_q4f16.onnx` (added) ↳ ✅ `bnb4`: `decoder_model_merged_bnb4.onnx` (added)b12eaab
-
Add/update the quantized ONNX model files and README.md for Transformers.js v3 (#1)
Verified signature- Add/update the quantized ONNX model files and README.md for Transformers.js v3 (0a2f2ca5ba7ebd1bd213e6fea2e4b578a1035cc8) Co-authored-by: Yuichiro Tachibana <whitphx@users.noreply.huggingface.co>6a8d2b5
-
[Automated] Update base model metadata
Verified signatureSet base model to "t5-base"31ba097
-
Upload fp16 ONNX weights
Verified signaturee69a4dc -
Upload fp16 ONNX weights
Verified signatureb957bfc
-
Upload folder using huggingface_hub
bda1337
-
Upload folder using huggingface_hub
e0941c5 -
Upload README.md with huggingface_hub
5c2dcce
-
Upload folder using huggingface_hub
5f0ec49 -
Upload README.md with huggingface_hub
ec12d06 -
initial commit
Joshuaac61cda