-
Delete _work/fp16/config.json with huggingface_hub
-
Delete _work/fp16/chat_template.jinja with huggingface_hub
-
Upload folder using huggingface_hub
-
Upload onnx/model_fp16.onnx with huggingface_hub
-
Upload onnx/model_quantized.onnx with huggingface_hub
-
Delete chat_template.jinja with huggingface_hub
-
Delete model.onnx with huggingface_hub
-
Delete onnx/model_q4.onnx with huggingface_hub
-
Delete onnx/model_int8.onnx with huggingface_hub
-
Delete onnx/model_fp16.onnx with huggingface_hub
-
Delete _work/q8/model_quantized.onnx with huggingface_hub
-
Delete _work/fp32/tokenizer_config.json with huggingface_hub
-
Delete _work/fp32/tokenizer.json with huggingface_hub
-
Delete _work/fp32/special_tokens_map.json with huggingface_hub
-
Delete _work/fp32/model.onnx with huggingface_hub
-
Delete _work/fp32/generation_config.json with huggingface_hub
-
Delete _work/fp32/config.json with huggingface_hub
-
Delete _work/fp32/chat_template.jinja with huggingface_hub
-
Delete _work/fp16/tokenizer_config.json with huggingface_hub
-
Delete _work/fp16/tokenizer.json with huggingface_hub
-
Delete _work/fp16/special_tokens_map.json with huggingface_hub
-
Delete _work/fp16/model.onnx with huggingface_hub
-
Delete _work/fp16/generation_config.json with huggingface_hub
-
Delete _work/fp16/config.json with huggingface_hub
-
Delete _work/fp16/chat_template.jinja with huggingface_hub
-
Upload folder using huggingface_hub
-
fix: re-export INT8 ONNX with KV cache (text-generation-with-past)
-
chore: remove root model.onnx (moved to onnx/model_int8.onnx)
-
feat: add INT8 quantized ONNX model at onnx/model_int8.onnx
-
feat: v2 retrained ONNX INT8 model (native FunctionGemma format)
-
Upload folder using huggingface_hub
-
Upload onnx/model_q4.onnx with huggingface_hub
-
Upload folder using huggingface_hub
-
Upload onnx/model_fp16.onnx with huggingface_hub
-
Delete onnx/model_quantized.onnx with huggingface_hub
-
Upload tokenizer_config.json with huggingface_hub
-
Upload config.json with huggingface_hub
-
Upload onnx/model.onnx with huggingface_hub
-
Upload onnx/model_quantized.onnx with huggingface_hub
-
Delete onnx/model_quantized.onnx with huggingface_hub
-
Delete model.onnx with huggingface_hub
-
Upload onnx/model_quantized.onnx with huggingface_hub
-
Upload folder using huggingface_hub
-
initial commit
