| { |
| "architectures": [ |
| "Qwen3_5ForConditionalGeneration" |
| ], |
| "dtype": "bfloat16", |
| "image_token_id": 248056, |
| "language_model_only": false, |
| "model_type": "qwen3_5", |
| "quantization_config": { |
| "autoround_version": "0.13.0", |
| "bits": 4, |
| "block_name_to_quantize": [ |
| "model.language_model.layers", |
| "mtp.layers" |
| ], |
| "data_type": "int", |
| "extra_config": { |
| ".*model\\.layers\\.0\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.0\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.0\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.0\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.0\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.0\\.mlp\\.down_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.0\\.mlp\\.gate_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.0\\.mlp\\.up_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.10\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.10\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.10\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.10\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.10\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.11\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.11\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.11\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.11\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.12\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.12\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.12\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.12\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.12\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.13\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.13\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.13\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.13\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.13\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.14\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.14\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.14\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.14\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.14\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.15\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.15\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.15\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.15\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.16\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.16\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.16\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.16\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.16\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.17\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.17\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.17\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.17\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.17\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.18\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.18\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.18\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.18\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.18\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.19\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.19\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.19\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.19\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.1\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.1\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.1\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.1\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.1\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.1\\.mlp\\.down_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.1\\.mlp\\.gate_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.1\\.mlp\\.up_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.20\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.20\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.20\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.20\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.20\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.21\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.21\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.21\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.21\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.21\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.22\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.22\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.22\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.22\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.22\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.23\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.23\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.23\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.23\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.24\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.24\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.24\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.24\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.24\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.25\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.25\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.25\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.25\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.25\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.26\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.26\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.26\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.26\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.26\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.27\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.27\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.27\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.27\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.28\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.28\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.28\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.28\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.28\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.29\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.29\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.29\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.29\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.29\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.2\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.2\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.2\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.2\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.2\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.2\\.mlp\\.down_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.2\\.mlp\\.gate_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.2\\.mlp\\.up_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.30\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.30\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.30\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.30\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.30\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.31\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.31\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.31\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.31\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.32\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.32\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.32\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.32\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.32\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.33\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.33\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.33\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.33\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.33\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.34\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.34\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.34\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.34\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.34\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.35\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.35\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.35\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.35\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.36\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.36\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.36\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.36\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.36\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.37\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.37\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.37\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.37\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.37\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.38\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.38\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.38\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.38\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.38\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.39\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.39\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.39\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.39\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.3\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.3\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.3\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.3\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.40\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.40\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.40\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.40\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.40\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.41\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.41\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.41\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.41\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.41\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.42\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.42\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.42\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.42\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.42\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.43\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.43\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.43\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.43\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.44\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.44\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.44\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.44\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.44\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.45\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.45\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.45\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.45\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.45\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.46\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.46\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.46\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.46\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.46\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.47\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.47\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.47\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.47\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.48\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.48\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.48\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.48\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.48\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.49\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.49\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.49\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.49\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.49\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.4\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.4\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.4\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.4\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.4\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.50\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.50\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.50\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.50\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.50\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.51\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.51\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.51\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.51\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.52\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.52\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.52\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.52\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.52\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.53\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.53\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.53\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.53\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.53\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.54\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.54\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.54\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.54\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.54\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.55\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.55\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.55\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.55\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.56\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.56\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.56\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.56\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.56\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.57\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.57\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.57\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.57\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.57\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.58\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.58\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.58\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.58\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.58\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.59\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.59\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.59\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.59\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.5\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.5\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.5\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.5\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.5\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.60\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.60\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.60\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.60\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.60\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.61\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.61\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.61\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.61\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.61\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.61\\.mlp\\.down_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.61\\.mlp\\.gate_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.61\\.mlp\\.up_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.62\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.62\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.62\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.62\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.62\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.62\\.mlp\\.down_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.62\\.mlp\\.gate_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.62\\.mlp\\.up_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.63\\.mlp\\.down_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.63\\.mlp\\.gate_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.63\\.mlp\\.up_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.63\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.63\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.63\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.63\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.6\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.6\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.6\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.6\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.6\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.7\\.self_attn\\.k_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.7\\.self_attn\\.o_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.7\\.self_attn\\.q_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.7\\.self_attn\\.v_proj.*": { |
| "bits": 8 |
| }, |
| ".*model\\.layers\\.8\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.8\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.8\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.8\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.8\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.9\\.linear_attn\\.in_proj_a.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.9\\.linear_attn\\.in_proj_b.*": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| ".*model\\.layers\\.9\\.linear_attn\\.in_proj_qkv.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.9\\.linear_attn\\.in_proj_z.*": { |
| "bits": 16 |
| }, |
| ".*model\\.layers\\.9\\.linear_attn\\.out_proj.*": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.0.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.0.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.0.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.0.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.0.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.0.mlp.down_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.0.mlp.gate_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.0.mlp.up_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.1.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.1.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.1.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.1.mlp.down_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.1.mlp.gate_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.1.mlp.up_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.10.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.10.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.10.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.11.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.11.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.11.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.11.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.12.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.12.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.12.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.13.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.13.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.13.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.14.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.14.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.14.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.15.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.15.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.15.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.15.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.16.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.16.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.16.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.17.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.17.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.17.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.18.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.18.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.18.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.19.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.19.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.19.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.19.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.2.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.2.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.2.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.2.mlp.down_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.2.mlp.gate_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.2.mlp.up_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.20.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.20.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.20.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.21.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.21.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.21.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.22.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.22.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.22.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.23.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.23.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.23.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.23.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.24.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.24.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.24.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.24.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.24.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.25.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.25.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.25.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.25.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.25.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.26.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.26.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.26.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.26.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.26.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.27.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.27.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.27.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.27.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.28.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.28.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.28.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.28.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.28.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.29.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.29.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.29.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.29.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.29.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.3.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.3.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.3.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.3.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.30.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.30.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.30.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.30.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.30.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.31.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.31.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.31.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.31.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.32.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.32.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.32.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.32.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.32.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.33.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.33.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.33.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.33.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.33.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.34.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.34.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.34.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.34.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.34.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.35.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.35.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.35.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.35.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.36.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.36.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.36.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.36.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.36.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.37.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.37.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.37.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.37.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.37.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.38.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.38.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.38.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.38.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.38.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.39.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.39.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.39.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.39.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.4.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.4.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.4.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.40.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.40.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.40.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.40.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.40.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.41.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.41.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.41.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.41.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.41.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.42.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.42.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.42.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.42.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.42.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.43.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.43.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.43.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.43.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.44.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.44.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.44.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.44.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.44.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.45.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.45.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.45.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.45.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.45.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.46.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.46.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.46.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.46.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.46.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.47.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.47.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.47.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.47.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.48.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.48.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.48.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.48.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.48.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.49.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.49.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.49.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.49.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.49.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.5.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.5.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.5.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.50.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.50.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.50.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.50.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.50.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.51.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.51.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.51.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.51.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.52.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.52.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.52.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.52.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.52.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.53.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.53.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.53.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.53.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.53.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.54.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.54.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.54.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.54.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.54.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.55.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.55.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.55.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.55.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.56.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.56.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.56.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.56.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.56.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.57.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.57.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.57.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.57.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.57.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.58.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.58.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.58.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.58.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.58.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.59.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.59.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.59.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.59.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.6.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.6.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.6.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.60.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.60.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.60.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.60.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.60.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.61.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.61.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.61.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.61.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.61.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.61.mlp.down_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.61.mlp.gate_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.61.mlp.up_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.62.linear_attn.in_proj_a": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.62.linear_attn.in_proj_b": { |
| "bits": 16, |
| "data_type": "fp" |
| }, |
| "model.language_model.layers.62.linear_attn.in_proj_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.62.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.62.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.62.mlp.down_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.62.mlp.gate_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.62.mlp.up_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.63.mlp.down_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.63.mlp.gate_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.63.mlp.up_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.63.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.63.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.63.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.63.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.7.self_attn.k_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.7.self_attn.o_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.7.self_attn.q_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.7.self_attn.v_proj": { |
| "bits": 8 |
| }, |
| "model.language_model.layers.8.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.8.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.8.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.9.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_qkv": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.9.linear_attn.in_proj_z": { |
| "bits": 16 |
| }, |
| "model.language_model.layers.9.linear_attn.out_proj": { |
| "bits": 16 |
| }, |
| "mtp.fc": { |
| "bits": 16, |
| "data_type": "fp" |
| } |
| }, |
| "group_size": 128, |
| "iters": 1000, |
| "nsamples": 512, |
| "packing_format": "auto_round:auto_gptq", |
| "quant_method": "auto-round", |
| "sym": true |
| }, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_output_gate": true, |
| "bos_token_id": 248044, |
| "dtype": "bfloat16", |
| "eos_token_id": 248044, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17408, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 48, |
| "linear_value_head_dim": 128, |
| "mamba_ssm_dtype": "float32", |
| "max_position_embeddings": 262144, |
| "model_type": "qwen3_5_text", |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 24, |
| "num_hidden_layers": 64, |
| "num_key_value_heads": 4, |
| "output_gate_type": "swish", |
| "pad_token_id": null, |
| "partial_rotary_factor": 0.25, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 10000000, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": false, |
| "use_cache": true, |
| "vocab_size": 248320 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.5.4", |
| "video_token_id": 248057, |
| "vision_config": { |
| "deepstack_visual_indexes": [], |
| "depth": 27, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "model_type": "qwen3_5", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 5120, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 248054, |
| "vision_start_token_id": 248053 |
| } |
