{ "model_id": "Qwen/Qwen3.6-27B", "model_type": "qwen3_5", "text_model_type": "qwen3_5_text", "is_moe": false, "dataset_id": "HuggingFaceH4/ultrachat_200k", "dataset_split": "train_sft", "dataset_offset": 0, "num_calibration_samples": 32, "calibration_token_target": 2000000, "calibration_max_samples": 5000, "shuffle_full_dataset": true, "max_seq_length": 16384, "seed": 3407, "ignore_profile": "auto_v16", "resolved_ignore_profile": "v16_dense", "ignore": [ "lm_head", "re:^mtp\\..*", "re:^model\\.visual\\..*", "re:.*linear_attn\\.in_proj_qkv$", "re:.*linear_attn\\.in_proj_z$", "re:.*linear_attn\\.in_proj_a$", "re:.*linear_attn\\.in_proj_b$" ], "pipeline": "basic", "moe_calibrate_all_experts": false, "sequential_targets": [], "sequential_offload_device": "cpu", "module_summary": { "total_linear_modules": 607, "quantized_linear_modules": 304, "ignored_linear_modules": 303, "ignored_module_names": [ "model.visual.blocks.0.attn.qkv", "model.visual.blocks.0.attn.proj", "model.visual.blocks.0.mlp.linear_fc1", "model.visual.blocks.0.mlp.linear_fc2", "model.visual.blocks.1.attn.qkv", "model.visual.blocks.1.attn.proj", "model.visual.blocks.1.mlp.linear_fc1", "model.visual.blocks.1.mlp.linear_fc2", "model.visual.blocks.2.attn.qkv", "model.visual.blocks.2.attn.proj", "model.visual.blocks.2.mlp.linear_fc1", "model.visual.blocks.2.mlp.linear_fc2", "model.visual.blocks.3.attn.qkv", "model.visual.blocks.3.attn.proj", "model.visual.blocks.3.mlp.linear_fc1", "model.visual.blocks.3.mlp.linear_fc2", "model.visual.blocks.4.attn.qkv", "model.visual.blocks.4.attn.proj", "model.visual.blocks.4.mlp.linear_fc1", "model.visual.blocks.4.mlp.linear_fc2", "model.visual.blocks.5.attn.qkv", "model.visual.blocks.5.attn.proj", "model.visual.blocks.5.mlp.linear_fc1", "model.visual.blocks.5.mlp.linear_fc2", "model.visual.blocks.6.attn.qkv", "model.visual.blocks.6.attn.proj", "model.visual.blocks.6.mlp.linear_fc1", "model.visual.blocks.6.mlp.linear_fc2", "model.visual.blocks.7.attn.qkv", "model.visual.blocks.7.attn.proj", "model.visual.blocks.7.mlp.linear_fc1", "model.visual.blocks.7.mlp.linear_fc2", "model.visual.blocks.8.attn.qkv", "model.visual.blocks.8.attn.proj", "model.visual.blocks.8.mlp.linear_fc1", "model.visual.blocks.8.mlp.linear_fc2", "model.visual.blocks.9.attn.qkv", "model.visual.blocks.9.attn.proj", "model.visual.blocks.9.mlp.linear_fc1", "model.visual.blocks.9.mlp.linear_fc2", "model.visual.blocks.10.attn.qkv", "model.visual.blocks.10.attn.proj", "model.visual.blocks.10.mlp.linear_fc1", "model.visual.blocks.10.mlp.linear_fc2", "model.visual.blocks.11.attn.qkv", "model.visual.blocks.11.attn.proj", "model.visual.blocks.11.mlp.linear_fc1", "model.visual.blocks.11.mlp.linear_fc2", "model.visual.blocks.12.attn.qkv", "model.visual.blocks.12.attn.proj", "model.visual.blocks.12.mlp.linear_fc1", "model.visual.blocks.12.mlp.linear_fc2", "model.visual.blocks.13.attn.qkv", "model.visual.blocks.13.attn.proj", "model.visual.blocks.13.mlp.linear_fc1", "model.visual.blocks.13.mlp.linear_fc2", "model.visual.blocks.14.attn.qkv", "model.visual.blocks.14.attn.proj", "model.visual.blocks.14.mlp.linear_fc1", "model.visual.blocks.14.mlp.linear_fc2", "model.visual.blocks.15.attn.qkv", "model.visual.blocks.15.attn.proj", "model.visual.blocks.15.mlp.linear_fc1", "model.visual.blocks.15.mlp.linear_fc2", "model.visual.blocks.16.attn.qkv", "model.visual.blocks.16.attn.proj", "model.visual.blocks.16.mlp.linear_fc1", "model.visual.blocks.16.mlp.linear_fc2", "model.visual.blocks.17.attn.qkv", "model.visual.blocks.17.attn.proj", "model.visual.blocks.17.mlp.linear_fc1", "model.visual.blocks.17.mlp.linear_fc2", "model.visual.blocks.18.attn.qkv", "model.visual.blocks.18.attn.proj", "model.visual.blocks.18.mlp.linear_fc1", "model.visual.blocks.18.mlp.linear_fc2", "model.visual.blocks.19.attn.qkv", "model.visual.blocks.19.attn.proj", "model.visual.blocks.19.mlp.linear_fc1", "model.visual.blocks.19.mlp.linear_fc2", "model.visual.blocks.20.attn.qkv", "model.visual.blocks.20.attn.proj", "model.visual.blocks.20.mlp.linear_fc1", "model.visual.blocks.20.mlp.linear_fc2", "model.visual.blocks.21.attn.qkv", "model.visual.blocks.21.attn.proj", "model.visual.blocks.21.mlp.linear_fc1", "model.visual.blocks.21.mlp.linear_fc2", "model.visual.blocks.22.attn.qkv", "model.visual.blocks.22.attn.proj", "model.visual.blocks.22.mlp.linear_fc1", "model.visual.blocks.22.mlp.linear_fc2", "model.visual.blocks.23.attn.qkv", "model.visual.blocks.23.attn.proj", "model.visual.blocks.23.mlp.linear_fc1", "model.visual.blocks.23.mlp.linear_fc2", "model.visual.blocks.24.attn.qkv", "model.visual.blocks.24.attn.proj", "model.visual.blocks.24.mlp.linear_fc1", "model.visual.blocks.24.mlp.linear_fc2", "model.visual.blocks.25.attn.qkv", "model.visual.blocks.25.attn.proj", "model.visual.blocks.25.mlp.linear_fc1", "model.visual.blocks.25.mlp.linear_fc2", "model.visual.blocks.26.attn.qkv", "model.visual.blocks.26.attn.proj", "model.visual.blocks.26.mlp.linear_fc1", "model.visual.blocks.26.mlp.linear_fc2", "model.visual.merger.linear_fc1", "model.visual.merger.linear_fc2", "model.language_model.layers.0.linear_attn.in_proj_qkv", "model.language_model.layers.0.linear_attn.in_proj_z", "model.language_model.layers.0.linear_attn.in_proj_b", "model.language_model.layers.0.linear_attn.in_proj_a", "model.language_model.layers.1.linear_attn.in_proj_qkv", "model.language_model.layers.1.linear_attn.in_proj_z", "model.language_model.layers.1.linear_attn.in_proj_b", "model.language_model.layers.1.linear_attn.in_proj_a", "model.language_model.layers.2.linear_attn.in_proj_qkv", "model.language_model.layers.2.linear_attn.in_proj_z", "model.language_model.layers.2.linear_attn.in_proj_b", "model.language_model.layers.2.linear_attn.in_proj_a", "model.language_model.layers.4.linear_attn.in_proj_qkv", "model.language_model.layers.4.linear_attn.in_proj_z", "model.language_model.layers.4.linear_attn.in_proj_b", "model.language_model.layers.4.linear_attn.in_proj_a", "model.language_model.layers.5.linear_attn.in_proj_qkv", "model.language_model.layers.5.linear_attn.in_proj_z", "model.language_model.layers.5.linear_attn.in_proj_b", "model.language_model.layers.5.linear_attn.in_proj_a", "model.language_model.layers.6.linear_attn.in_proj_qkv", "model.language_model.layers.6.linear_attn.in_proj_z", "model.language_model.layers.6.linear_attn.in_proj_b", "model.language_model.layers.6.linear_attn.in_proj_a", "model.language_model.layers.8.linear_attn.in_proj_qkv", "model.language_model.layers.8.linear_attn.in_proj_z", "model.language_model.layers.8.linear_attn.in_proj_b", "model.language_model.layers.8.linear_attn.in_proj_a", "model.language_model.layers.9.linear_attn.in_proj_qkv", "model.language_model.layers.9.linear_attn.in_proj_z", "model.language_model.layers.9.linear_attn.in_proj_b", "model.language_model.layers.9.linear_attn.in_proj_a", "model.language_model.layers.10.linear_attn.in_proj_qkv", "model.language_model.layers.10.linear_attn.in_proj_z", "model.language_model.layers.10.linear_attn.in_proj_b", "model.language_model.layers.10.linear_attn.in_proj_a", "model.language_model.layers.12.linear_attn.in_proj_qkv", "model.language_model.layers.12.linear_attn.in_proj_z", "model.language_model.layers.12.linear_attn.in_proj_b", "model.language_model.layers.12.linear_attn.in_proj_a", "model.language_model.layers.13.linear_attn.in_proj_qkv", "model.language_model.layers.13.linear_attn.in_proj_z", "model.language_model.layers.13.linear_attn.in_proj_b", "model.language_model.layers.13.linear_attn.in_proj_a", "model.language_model.layers.14.linear_attn.in_proj_qkv", "model.language_model.layers.14.linear_attn.in_proj_z", "model.language_model.layers.14.linear_attn.in_proj_b", "model.language_model.layers.14.linear_attn.in_proj_a", "model.language_model.layers.16.linear_attn.in_proj_qkv", "model.language_model.layers.16.linear_attn.in_proj_z", "model.language_model.layers.16.linear_attn.in_proj_b", "model.language_model.layers.16.linear_attn.in_proj_a", "model.language_model.layers.17.linear_attn.in_proj_qkv", "model.language_model.layers.17.linear_attn.in_proj_z", "model.language_model.layers.17.linear_attn.in_proj_b", "model.language_model.layers.17.linear_attn.in_proj_a", "model.language_model.layers.18.linear_attn.in_proj_qkv", "model.language_model.layers.18.linear_attn.in_proj_z", "model.language_model.layers.18.linear_attn.in_proj_b", "model.language_model.layers.18.linear_attn.in_proj_a", "model.language_model.layers.20.linear_attn.in_proj_qkv", "model.language_model.layers.20.linear_attn.in_proj_z", "model.language_model.layers.20.linear_attn.in_proj_b", "model.language_model.layers.20.linear_attn.in_proj_a", "model.language_model.layers.21.linear_attn.in_proj_qkv", "model.language_model.layers.21.linear_attn.in_proj_z", "model.language_model.layers.21.linear_attn.in_proj_b", "model.language_model.layers.21.linear_attn.in_proj_a", "model.language_model.layers.22.linear_attn.in_proj_qkv", "model.language_model.layers.22.linear_attn.in_proj_z", "model.language_model.layers.22.linear_attn.in_proj_b", "model.language_model.layers.22.linear_attn.in_proj_a", "model.language_model.layers.24.linear_attn.in_proj_qkv", "model.language_model.layers.24.linear_attn.in_proj_z", "model.language_model.layers.24.linear_attn.in_proj_b", "model.language_model.layers.24.linear_attn.in_proj_a", "model.language_model.layers.25.linear_attn.in_proj_qkv", "model.language_model.layers.25.linear_attn.in_proj_z", "model.language_model.layers.25.linear_attn.in_proj_b", "model.language_model.layers.25.linear_attn.in_proj_a", "model.language_model.layers.26.linear_attn.in_proj_qkv", "model.language_model.layers.26.linear_attn.in_proj_z", "model.language_model.layers.26.linear_attn.in_proj_b", "model.language_model.layers.26.linear_attn.in_proj_a", "model.language_model.layers.28.linear_attn.in_proj_qkv", "model.language_model.layers.28.linear_attn.in_proj_z", "model.language_model.layers.28.linear_attn.in_proj_b", "model.language_model.layers.28.linear_attn.in_proj_a", "model.language_model.layers.29.linear_attn.in_proj_qkv", "model.language_model.layers.29.linear_attn.in_proj_z", "model.language_model.layers.29.linear_attn.in_proj_b", "model.language_model.layers.29.linear_attn.in_proj_a", "model.language_model.layers.30.linear_attn.in_proj_qkv", "model.language_model.layers.30.linear_attn.in_proj_z", "model.language_model.layers.30.linear_attn.in_proj_b", "model.language_model.layers.30.linear_attn.in_proj_a", "model.language_model.layers.32.linear_attn.in_proj_qkv", "model.language_model.layers.32.linear_attn.in_proj_z", "model.language_model.layers.32.linear_attn.in_proj_b", "model.language_model.layers.32.linear_attn.in_proj_a", "model.language_model.layers.33.linear_attn.in_proj_qkv", "model.language_model.layers.33.linear_attn.in_proj_z", "model.language_model.layers.33.linear_attn.in_proj_b", "model.language_model.layers.33.linear_attn.in_proj_a", "model.language_model.layers.34.linear_attn.in_proj_qkv", "model.language_model.layers.34.linear_attn.in_proj_z", "model.language_model.layers.34.linear_attn.in_proj_b", "model.language_model.layers.34.linear_attn.in_proj_a", "model.language_model.layers.36.linear_attn.in_proj_qkv", "model.language_model.layers.36.linear_attn.in_proj_z", "model.language_model.layers.36.linear_attn.in_proj_b", "model.language_model.layers.36.linear_attn.in_proj_a", "model.language_model.layers.37.linear_attn.in_proj_qkv", "model.language_model.layers.37.linear_attn.in_proj_z", "model.language_model.layers.37.linear_attn.in_proj_b", "model.language_model.layers.37.linear_attn.in_proj_a", "model.language_model.layers.38.linear_attn.in_proj_qkv", "model.language_model.layers.38.linear_attn.in_proj_z", "model.language_model.layers.38.linear_attn.in_proj_b", "model.language_model.layers.38.linear_attn.in_proj_a", "model.language_model.layers.40.linear_attn.in_proj_qkv", "model.language_model.layers.40.linear_attn.in_proj_z", "model.language_model.layers.40.linear_attn.in_proj_b", "model.language_model.layers.40.linear_attn.in_proj_a", "model.language_model.layers.41.linear_attn.in_proj_qkv", "model.language_model.layers.41.linear_attn.in_proj_z", "model.language_model.layers.41.linear_attn.in_proj_b", "model.language_model.layers.41.linear_attn.in_proj_a", "model.language_model.layers.42.linear_attn.in_proj_qkv", "model.language_model.layers.42.linear_attn.in_proj_z", "model.language_model.layers.42.linear_attn.in_proj_b", "model.language_model.layers.42.linear_attn.in_proj_a", "model.language_model.layers.44.linear_attn.in_proj_qkv", "model.language_model.layers.44.linear_attn.in_proj_z", "model.language_model.layers.44.linear_attn.in_proj_b", "model.language_model.layers.44.linear_attn.in_proj_a", "model.language_model.layers.45.linear_attn.in_proj_qkv", "model.language_model.layers.45.linear_attn.in_proj_z", "model.language_model.layers.45.linear_attn.in_proj_b", "model.language_model.layers.45.linear_attn.in_proj_a", "model.language_model.layers.46.linear_attn.in_proj_qkv", "model.language_model.layers.46.linear_attn.in_proj_z", "model.language_model.layers.46.linear_attn.in_proj_b", "model.language_model.layers.46.linear_attn.in_proj_a", "model.language_model.layers.48.linear_attn.in_proj_qkv", "model.language_model.layers.48.linear_attn.in_proj_z", "model.language_model.layers.48.linear_attn.in_proj_b", "model.language_model.layers.48.linear_attn.in_proj_a", "model.language_model.layers.49.linear_attn.in_proj_qkv", "model.language_model.layers.49.linear_attn.in_proj_z", "model.language_model.layers.49.linear_attn.in_proj_b", "model.language_model.layers.49.linear_attn.in_proj_a", "model.language_model.layers.50.linear_attn.in_proj_qkv", "model.language_model.layers.50.linear_attn.in_proj_z", "model.language_model.layers.50.linear_attn.in_proj_b", "model.language_model.layers.50.linear_attn.in_proj_a", "model.language_model.layers.52.linear_attn.in_proj_qkv", "model.language_model.layers.52.linear_attn.in_proj_z", "model.language_model.layers.52.linear_attn.in_proj_b", "model.language_model.layers.52.linear_attn.in_proj_a", "model.language_model.layers.53.linear_attn.in_proj_qkv", "model.language_model.layers.53.linear_attn.in_proj_z", "model.language_model.layers.53.linear_attn.in_proj_b", "model.language_model.layers.53.linear_attn.in_proj_a", "model.language_model.layers.54.linear_attn.in_proj_qkv", "model.language_model.layers.54.linear_attn.in_proj_z", "model.language_model.layers.54.linear_attn.in_proj_b", "model.language_model.layers.54.linear_attn.in_proj_a", "model.language_model.layers.56.linear_attn.in_proj_qkv", "model.language_model.layers.56.linear_attn.in_proj_z", "model.language_model.layers.56.linear_attn.in_proj_b", "model.language_model.layers.56.linear_attn.in_proj_a", "model.language_model.layers.57.linear_attn.in_proj_qkv", "model.language_model.layers.57.linear_attn.in_proj_z", "model.language_model.layers.57.linear_attn.in_proj_b", "model.language_model.layers.57.linear_attn.in_proj_a", "model.language_model.layers.58.linear_attn.in_proj_qkv", "model.language_model.layers.58.linear_attn.in_proj_z", "model.language_model.layers.58.linear_attn.in_proj_b", "model.language_model.layers.58.linear_attn.in_proj_a", "model.language_model.layers.60.linear_attn.in_proj_qkv", "model.language_model.layers.60.linear_attn.in_proj_z", "model.language_model.layers.60.linear_attn.in_proj_b", "model.language_model.layers.60.linear_attn.in_proj_a", "model.language_model.layers.61.linear_attn.in_proj_qkv", "model.language_model.layers.61.linear_attn.in_proj_z", "model.language_model.layers.61.linear_attn.in_proj_b", "model.language_model.layers.61.linear_attn.in_proj_a", "model.language_model.layers.62.linear_attn.in_proj_qkv", "model.language_model.layers.62.linear_attn.in_proj_z", "model.language_model.layers.62.linear_attn.in_proj_b", "model.language_model.layers.62.linear_attn.in_proj_a", "lm_head" ] }, "calibration_summary": { "mode": "token_budget", "requested_num_calibration_samples": 32, "selected_num_calibration_samples": 1629, "calibration_token_target": 2000000, "selected_calibration_tokens": 2001551, "truncated_samples": 0, "min_tokens": 141, "max_tokens": 4051, "mean_tokens": 1228.6992019643953 } }