Download Ref2VA/text_encoder/quantization_config.json from intel-ai/MiniMax-H3-MXFP8-CT-AutoRound: direct link, hf CLI and curl.
- Browser
- Download file 420 Bytes
-
https://huggingface.co/intel-ai/MiniMax-H3-MXFP8-CT-AutoRound/resolve/main/Ref2VA/text_encoder/quantization_config.json
- Command line
-
hf download hf://intel-ai/MiniMax-H3-MXFP8-CT-AutoRound/Ref2VA/text_encoder/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/intel-ai/MiniMax-H3-MXFP8-CT-AutoRound/resolve/main/Ref2VA/text_encoder/quantization_config.json
420 Bytes
| { | |
| "bits": 8, | |
| "act_bits": 8, | |
| "data_type": "mx_fp", | |
| "act_data_type": "mx_fp", | |
| "group_size": 32, | |
| "act_group_size": 32, | |
| "sym": true, | |
| "act_sym": true, | |
| "act_dynamic": true, | |
| "enable_quanted_input": false, | |
| "low_gpu_mem_usage": true, | |
| "autoround_version": "0.17.0", | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:llm_compressor" | |
| } |