Download quantization_config.json from Intel/Qwen3.5-2B-int4-AutoRound: direct link, hf CLI and curl.
- Browser
- Download file 4.25 kB
-
https://huggingface.co/Intel/Qwen3.5-2B-int4-AutoRound/resolve/main/quantization_config.json
- Command line
-
hf download hf://Intel/Qwen3.5-2B-int4-AutoRound/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/Intel/Qwen3.5-2B-int4-AutoRound/resolve/main/quantization_config.json
4.25 kB
| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 128, | |
| "sym": true, | |
| "autoround_version": "0.12.0", | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "extra_config": { | |
| "model.language_model.layers.0.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.0.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.1.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.1.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.2.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.2.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.4.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.4.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.5.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.5.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.6.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.6.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.8.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.8.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.9.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.9.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.10.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.10.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.12.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.12.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.13.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.13.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.14.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.14.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.16.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.16.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.17.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.17.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.18.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.18.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.20.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.20.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.21.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.21.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.22.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.22.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| } | |
| } | |
| } |