| { |
| "bits": 4, |
| "data_type": "int", |
| "group_size": 128, |
| "sym": true, |
| "enable_quanted_input": false, |
| "low_gpu_mem_usage": true, |
| "static_attention_granularity": "tensor", |
| "static_kv_granularity": "tensor", |
| "autoround_version": "0.15.0", |
| "block_name_to_quantize": "model.layers", |
| "quant_method": "auto-round", |
| "packing_format": "auto_round:auto_gptq", |
| "extra_config": { |
| ".*model\\.layers\\.0\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.1\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.2\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.3\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.4\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.5\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.6\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.7\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.8\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.9\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.10\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.11\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.12\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.13\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.14\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.15\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.16\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.17\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.18\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.19\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.20\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.21\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.22\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.23\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.24\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.25\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.26\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.27\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.28\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.29\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.30\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.31\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.32\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.33\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.34\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.35\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.36\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.37\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.38\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.39\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.40\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.41\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| }, |
| ".*model\\.layers\\.42\\.mlp\\.gate.*": { |
| "bits": 16, |
| "data_type": "float" |
| } |
| } |
| } |
