Download quantization_config.json from Vishva007/NuExtract3-W4A16-AutoRound: direct link, hf CLI and curl.
- Browser
- Download file 450 Bytes
-
https://huggingface.co/Vishva007/NuExtract3-W4A16-AutoRound/resolve/main/quantization_config.json
- Command line
-
hf download hf://Vishva007/NuExtract3-W4A16-AutoRound/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/Vishva007/NuExtract3-W4A16-AutoRound/resolve/main/quantization_config.json
450 Bytes
| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 32, | |
| "sym": true, | |
| "batch_size": 1, | |
| "iters": 1000, | |
| "nsamples": 512, | |
| "seqlen": 4096, | |
| "autoround_version": "0.14.2", | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "extra_config": { | |
| ".*mtp.*": { | |
| "data_type": "bfloat16" | |
| }, | |
| ".*mtp\\.fc.*": { | |
| "data_type": "bfloat16" | |
| } | |
| } | |
| } |