Download quantization_config.json from kaitchup/GLM-4.7-Flash-autoround-w4a16: direct link, hf CLI and curl.
- Browser
- Download file 509 Bytes
-
https://huggingface.co/kaitchup/GLM-4.7-Flash-autoround-w4a16/resolve/main/quantization_config.json
- Command line
-
hf download hf://kaitchup/GLM-4.7-Flash-autoround-w4a16/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/kaitchup/GLM-4.7-Flash-autoround-w4a16/resolve/main/quantization_config.json
509 Bytes
| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 128, | |
| "sym": true, | |
| "iters": 1000, | |
| "nsamples": 512, | |
| "autoround_version": "0.9.6", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "extra_config": { | |
| "model.layers.0.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.layers.0.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.layers.0.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| } | |
| } | |
| } |