Upload optimized ONNX files w/ GQA

Upload optimized ONNX files w/ GQA

Upload optimized ONNX files w/ GQA

Delete onnx/model_uint8.onnx

Delete onnx/model_quantized.onnx

Delete onnx/model_q4f16.onnx

Delete onnx/model_int8.onnx

Delete onnx/model_bnb4.onnx

Delete onnx/model_q4.onnx

Delete onnx/model_fp16.onnx_data

Delete onnx/model_fp16.onnx

Delete onnx/model.onnx_data

Delete onnx/model.onnx

Upload optimized ONNX files w/ GQA

Update config.json

Update config.json

Upload optimized vision/embedding models

Upload optimized ONNX files

[Automated] Update base model metadata

Update README.md

Upload folder using huggingface_hub

Update post-processor

Delete onnx/input_embeds.onnx

Delete onnx/input_embeds_bnb4.onnx

Delete onnx/input_embeds_fp16.onnx

Delete onnx/input_embeds_int8.onnx

Delete onnx/input_embeds_q4.onnx

Delete onnx/input_embeds_quantized.onnx

Delete onnx/input_embeds_uint8.onnx

Update generation_config.json

Upload config.json

Upload fixed weights (reduce_range=false, per_channel=false) (#5)

Upload 5 files

Delete onnx/model.onnx_data

Delete onnx/model.onnx

Delete onnx/decoder_with_past_model_uint8.onnx

Delete onnx/decoder_with_past_model_quantized.onnx

Delete onnx/decoder_with_past_model_q4.onnx

Delete onnx/decoder_with_past_model_int8.onnx

Delete onnx/decoder_with_past_model_bnb4.onnx

Upload new weights (#4)

Upload new weights (#3)

Upload new weights (#2)

Upload folder using huggingface_hub

Update config.json

Update README.md

Update preprocessor_config.json

Create preprocessor_config.json

Update config.json

Upload folder using huggingface_hub