| { |
| "model_config": { |
| "name": "Qwen_Omni", |
| "model_path": "Base Model Path", |
| "trust_remote_code": true, |
| "torch_dtype": "auto", |
| "device_map": "auto", |
| "low_cpu_mem_usage": true, |
| "use_cache": false, |
| "cache_dir": null, |
| "use_audio_in_video": false, |
| "attn_implementation": "flash_attention_2" |
| }, |
| "compression_config": { |
| "name": [ |
| "PTQ" |
| ], |
| "quantization": { |
| "name": "fp8_dynamic", |
| "save_name": "compressed-tensors", |
| "bits": 8, |
| "quant_method": { |
| "weight": "per-tensor", |
| "activation": "per-tensor" |
| }, |
| "quant_helpers": [], |
| "smooth_alpha": 0.5, |
| "low_memory": false, |
| "cpu_convert": false, |
| "modules_to_quantize": [], |
| "zero_point": true, |
| "mse_range": false, |
| "ignore_layers": [ |
| "thinker.audio_tower.layers.0.self_attn.k_proj", |
| "thinker.audio_tower.layers.0.self_attn.v_proj", |
| "thinker.audio_tower.layers.0.self_attn.q_proj", |
| "thinker.audio_tower.layers.0.self_attn.out_proj", |
| "thinker.audio_tower.layers.0.fc1", |
| "thinker.audio_tower.layers.0.fc2", |
| "thinker.audio_tower.layers.1.self_attn.k_proj", |
| "thinker.audio_tower.layers.1.self_attn.v_proj", |
| "thinker.audio_tower.layers.1.self_attn.q_proj", |
| "thinker.audio_tower.layers.1.self_attn.out_proj", |
| "thinker.audio_tower.layers.1.fc1", |
| "thinker.audio_tower.layers.1.fc2", |
| "thinker.audio_tower.layers.2.self_attn.k_proj", |
| "thinker.audio_tower.layers.2.self_attn.v_proj", |
| "thinker.audio_tower.layers.2.self_attn.q_proj", |
| "thinker.audio_tower.layers.2.self_attn.out_proj", |
| "thinker.audio_tower.layers.2.fc1", |
| "thinker.audio_tower.layers.2.fc2", |
| "thinker.audio_tower.layers.3.self_attn.k_proj", |
| "thinker.audio_tower.layers.3.self_attn.v_proj", |
| "thinker.audio_tower.layers.3.self_attn.q_proj", |
| "thinker.audio_tower.layers.3.self_attn.out_proj", |
| "thinker.audio_tower.layers.3.fc1", |
| "thinker.audio_tower.layers.3.fc2", |
| "thinker.audio_tower.layers.4.self_attn.k_proj", |
| "thinker.audio_tower.layers.4.self_attn.v_proj", |
| "thinker.audio_tower.layers.4.self_attn.q_proj", |
| "thinker.audio_tower.layers.4.self_attn.out_proj", |
| "thinker.audio_tower.layers.4.fc1", |
| "thinker.audio_tower.layers.4.fc2", |
| "thinker.audio_tower.layers.5.self_attn.k_proj", |
| "thinker.audio_tower.layers.5.self_attn.v_proj", |
| "thinker.audio_tower.layers.5.self_attn.q_proj", |
| "thinker.audio_tower.layers.5.self_attn.out_proj", |
| "thinker.audio_tower.layers.5.fc1", |
| "thinker.audio_tower.layers.5.fc2", |
| "thinker.audio_tower.layers.6.self_attn.k_proj", |
| "thinker.audio_tower.layers.6.self_attn.v_proj", |
| "thinker.audio_tower.layers.6.self_attn.q_proj", |
| "thinker.audio_tower.layers.6.self_attn.out_proj", |
| "thinker.audio_tower.layers.6.fc1", |
| "thinker.audio_tower.layers.6.fc2", |
| "thinker.audio_tower.layers.7.self_attn.k_proj", |
| "thinker.audio_tower.layers.7.self_attn.v_proj", |
| "thinker.audio_tower.layers.7.self_attn.q_proj", |
| "thinker.audio_tower.layers.7.self_attn.out_proj", |
| "thinker.audio_tower.layers.7.fc1", |
| "thinker.audio_tower.layers.7.fc2", |
| "thinker.audio_tower.layers.8.self_attn.k_proj", |
| "thinker.audio_tower.layers.8.self_attn.v_proj", |
| "thinker.audio_tower.layers.8.self_attn.q_proj", |
| "thinker.audio_tower.layers.8.self_attn.out_proj", |
| "thinker.audio_tower.layers.8.fc1", |
| "thinker.audio_tower.layers.8.fc2", |
| "thinker.audio_tower.layers.9.self_attn.k_proj", |
| "thinker.audio_tower.layers.9.self_attn.v_proj", |
| "thinker.audio_tower.layers.9.self_attn.q_proj", |
| "thinker.audio_tower.layers.9.self_attn.out_proj", |
| "thinker.audio_tower.layers.9.fc1", |
| "thinker.audio_tower.layers.9.fc2", |
| "thinker.audio_tower.layers.10.self_attn.k_proj", |
| "thinker.audio_tower.layers.10.self_attn.v_proj", |
| "thinker.audio_tower.layers.10.self_attn.q_proj", |
| "thinker.audio_tower.layers.10.self_attn.out_proj", |
| "thinker.audio_tower.layers.10.fc1", |
| "thinker.audio_tower.layers.10.fc2", |
| "thinker.audio_tower.layers.11.self_attn.k_proj", |
| "thinker.audio_tower.layers.11.self_attn.v_proj", |
| "thinker.audio_tower.layers.11.self_attn.q_proj", |
| "thinker.audio_tower.layers.11.self_attn.out_proj", |
| "thinker.audio_tower.layers.11.fc1", |
| "thinker.audio_tower.layers.11.fc2", |
| "thinker.audio_tower.layers.12.self_attn.k_proj", |
| "thinker.audio_tower.layers.12.self_attn.v_proj", |
| "thinker.audio_tower.layers.12.self_attn.q_proj", |
| "thinker.audio_tower.layers.12.self_attn.out_proj", |
| "thinker.audio_tower.layers.12.fc1", |
| "thinker.audio_tower.layers.12.fc2", |
| "thinker.audio_tower.layers.13.self_attn.k_proj", |
| "thinker.audio_tower.layers.13.self_attn.v_proj", |
| "thinker.audio_tower.layers.13.self_attn.q_proj", |
| "thinker.audio_tower.layers.13.self_attn.out_proj", |
| "thinker.audio_tower.layers.13.fc1", |
| "thinker.audio_tower.layers.13.fc2", |
| "thinker.audio_tower.layers.14.self_attn.k_proj", |
| "thinker.audio_tower.layers.14.self_attn.v_proj", |
| "thinker.audio_tower.layers.14.self_attn.q_proj", |
| "thinker.audio_tower.layers.14.self_attn.out_proj", |
| "thinker.audio_tower.layers.14.fc1", |
| "thinker.audio_tower.layers.14.fc2", |
| "thinker.audio_tower.layers.15.self_attn.k_proj", |
| "thinker.audio_tower.layers.15.self_attn.v_proj", |
| "thinker.audio_tower.layers.15.self_attn.q_proj", |
| "thinker.audio_tower.layers.15.self_attn.out_proj", |
| "thinker.audio_tower.layers.15.fc1", |
| "thinker.audio_tower.layers.15.fc2", |
| "thinker.audio_tower.layers.16.self_attn.k_proj", |
| "thinker.audio_tower.layers.16.self_attn.v_proj", |
| "thinker.audio_tower.layers.16.self_attn.q_proj", |
| "thinker.audio_tower.layers.16.self_attn.out_proj", |
| "thinker.audio_tower.layers.16.fc1", |
| "thinker.audio_tower.layers.16.fc2", |
| "thinker.audio_tower.layers.17.self_attn.k_proj", |
| "thinker.audio_tower.layers.17.self_attn.v_proj", |
| "thinker.audio_tower.layers.17.self_attn.q_proj", |
| "thinker.audio_tower.layers.17.self_attn.out_proj", |
| "thinker.audio_tower.layers.17.fc1", |
| "thinker.audio_tower.layers.17.fc2", |
| "thinker.audio_tower.layers.18.self_attn.k_proj", |
| "thinker.audio_tower.layers.18.self_attn.v_proj", |
| "thinker.audio_tower.layers.18.self_attn.q_proj", |
| "thinker.audio_tower.layers.18.self_attn.out_proj", |
| "thinker.audio_tower.layers.18.fc1", |
| "thinker.audio_tower.layers.18.fc2", |
| "thinker.audio_tower.layers.19.self_attn.k_proj", |
| "thinker.audio_tower.layers.19.self_attn.v_proj", |
| "thinker.audio_tower.layers.19.self_attn.q_proj", |
| "thinker.audio_tower.layers.19.self_attn.out_proj", |
| "thinker.audio_tower.layers.19.fc1", |
| "thinker.audio_tower.layers.19.fc2", |
| "thinker.audio_tower.layers.20.self_attn.k_proj", |
| "thinker.audio_tower.layers.20.self_attn.v_proj", |
| "thinker.audio_tower.layers.20.self_attn.q_proj", |
| "thinker.audio_tower.layers.20.self_attn.out_proj", |
| "thinker.audio_tower.layers.20.fc1", |
| "thinker.audio_tower.layers.20.fc2", |
| "thinker.audio_tower.layers.21.self_attn.k_proj", |
| "thinker.audio_tower.layers.21.self_attn.v_proj", |
| "thinker.audio_tower.layers.21.self_attn.q_proj", |
| "thinker.audio_tower.layers.21.self_attn.out_proj", |
| "thinker.audio_tower.layers.21.fc1", |
| "thinker.audio_tower.layers.21.fc2", |
| "thinker.audio_tower.layers.22.self_attn.k_proj", |
| "thinker.audio_tower.layers.22.self_attn.v_proj", |
| "thinker.audio_tower.layers.22.self_attn.q_proj", |
| "thinker.audio_tower.layers.22.self_attn.out_proj", |
| "thinker.audio_tower.layers.22.fc1", |
| "thinker.audio_tower.layers.22.fc2", |
| "thinker.audio_tower.layers.23.self_attn.k_proj", |
| "thinker.audio_tower.layers.23.self_attn.v_proj", |
| "thinker.audio_tower.layers.23.self_attn.q_proj", |
| "thinker.audio_tower.layers.23.self_attn.out_proj", |
| "thinker.audio_tower.layers.23.fc1", |
| "thinker.audio_tower.layers.23.fc2", |
| "thinker.audio_tower.layers.24.self_attn.k_proj", |
| "thinker.audio_tower.layers.24.self_attn.v_proj", |
| "thinker.audio_tower.layers.24.self_attn.q_proj", |
| "thinker.audio_tower.layers.24.self_attn.out_proj", |
| "thinker.audio_tower.layers.24.fc1", |
| "thinker.audio_tower.layers.24.fc2", |
| "thinker.audio_tower.layers.25.self_attn.k_proj", |
| "thinker.audio_tower.layers.25.self_attn.v_proj", |
| "thinker.audio_tower.layers.25.self_attn.q_proj", |
| "thinker.audio_tower.layers.25.self_attn.out_proj", |
| "thinker.audio_tower.layers.25.fc1", |
| "thinker.audio_tower.layers.25.fc2", |
| "thinker.audio_tower.layers.26.self_attn.k_proj", |
| "thinker.audio_tower.layers.26.self_attn.v_proj", |
| "thinker.audio_tower.layers.26.self_attn.q_proj", |
| "thinker.audio_tower.layers.26.self_attn.out_proj", |
| "thinker.audio_tower.layers.26.fc1", |
| "thinker.audio_tower.layers.26.fc2", |
| "thinker.audio_tower.layers.27.self_attn.k_proj", |
| "thinker.audio_tower.layers.27.self_attn.v_proj", |
| "thinker.audio_tower.layers.27.self_attn.q_proj", |
| "thinker.audio_tower.layers.27.self_attn.out_proj", |
| "thinker.audio_tower.layers.27.fc1", |
| "thinker.audio_tower.layers.27.fc2", |
| "thinker.audio_tower.layers.28.self_attn.k_proj", |
| "thinker.audio_tower.layers.28.self_attn.v_proj", |
| "thinker.audio_tower.layers.28.self_attn.q_proj", |
| "thinker.audio_tower.layers.28.self_attn.out_proj", |
| "thinker.audio_tower.layers.28.fc1", |
| "thinker.audio_tower.layers.28.fc2", |
| "thinker.audio_tower.layers.29.self_attn.k_proj", |
| "thinker.audio_tower.layers.29.self_attn.v_proj", |
| "thinker.audio_tower.layers.29.self_attn.q_proj", |
| "thinker.audio_tower.layers.29.self_attn.out_proj", |
| "thinker.audio_tower.layers.29.fc1", |
| "thinker.audio_tower.layers.29.fc2", |
| "thinker.audio_tower.layers.30.self_attn.k_proj", |
| "thinker.audio_tower.layers.30.self_attn.v_proj", |
| "thinker.audio_tower.layers.30.self_attn.q_proj", |
| "thinker.audio_tower.layers.30.self_attn.out_proj", |
| "thinker.audio_tower.layers.30.fc1", |
| "thinker.audio_tower.layers.30.fc2", |
| "thinker.audio_tower.layers.31.self_attn.k_proj", |
| "thinker.audio_tower.layers.31.self_attn.v_proj", |
| "thinker.audio_tower.layers.31.self_attn.q_proj", |
| "thinker.audio_tower.layers.31.self_attn.out_proj", |
| "thinker.audio_tower.layers.31.fc1", |
| "thinker.audio_tower.layers.31.fc2", |
| "thinker.audio_tower.conv_out", |
| "thinker.audio_tower.proj1", |
| "thinker.audio_tower.proj2", |
| "thinker.visual.merger_list.0.mlp.0", |
| "thinker.visual.merger_list.0.mlp.2", |
| "thinker.visual.merger_list.1.mlp.0", |
| "thinker.visual.merger_list.1.mlp.2", |
| "thinker.visual.merger_list.2.mlp.0", |
| "thinker.visual.merger_list.2.mlp.2", |
| "thinker.visual.blocks.0.attn.qkv", |
| "thinker.visual.blocks.0.attn.proj", |
| "thinker.visual.blocks.0.mlp.linear_fc1", |
| "thinker.visual.blocks.0.mlp.linear_fc2", |
| "thinker.visual.blocks.1.attn.qkv", |
| "thinker.visual.blocks.1.attn.proj", |
| "thinker.visual.blocks.1.mlp.linear_fc1", |
| "thinker.visual.blocks.1.mlp.linear_fc2", |
| "thinker.visual.blocks.2.attn.qkv", |
| "thinker.visual.blocks.2.attn.proj", |
| "thinker.visual.blocks.2.mlp.linear_fc1", |
| "thinker.visual.blocks.2.mlp.linear_fc2", |
| "thinker.visual.blocks.3.attn.qkv", |
| "thinker.visual.blocks.3.attn.proj", |
| "thinker.visual.blocks.3.mlp.linear_fc1", |
| "thinker.visual.blocks.3.mlp.linear_fc2", |
| "thinker.visual.blocks.4.attn.qkv", |
| "thinker.visual.blocks.4.attn.proj", |
| "thinker.visual.blocks.4.mlp.linear_fc1", |
| "thinker.visual.blocks.4.mlp.linear_fc2", |
| "thinker.visual.blocks.5.attn.qkv", |
| "thinker.visual.blocks.5.attn.proj", |
| "thinker.visual.blocks.5.mlp.linear_fc1", |
| "thinker.visual.blocks.5.mlp.linear_fc2", |
| "thinker.visual.blocks.6.attn.qkv", |
| "thinker.visual.blocks.6.attn.proj", |
| "thinker.visual.blocks.6.mlp.linear_fc1", |
| "thinker.visual.blocks.6.mlp.linear_fc2", |
| "thinker.visual.blocks.7.attn.qkv", |
| "thinker.visual.blocks.7.attn.proj", |
| "thinker.visual.blocks.7.mlp.linear_fc1", |
| "thinker.visual.blocks.7.mlp.linear_fc2", |
| "thinker.visual.blocks.8.attn.qkv", |
| "thinker.visual.blocks.8.attn.proj", |
| "thinker.visual.blocks.8.mlp.linear_fc1", |
| "thinker.visual.blocks.8.mlp.linear_fc2", |
| "thinker.visual.blocks.9.attn.qkv", |
| "thinker.visual.blocks.9.attn.proj", |
| "thinker.visual.blocks.9.mlp.linear_fc1", |
| "thinker.visual.blocks.9.mlp.linear_fc2", |
| "thinker.visual.blocks.10.attn.qkv", |
| "thinker.visual.blocks.10.attn.proj", |
| "thinker.visual.blocks.10.mlp.linear_fc1", |
| "thinker.visual.blocks.10.mlp.linear_fc2", |
| "thinker.visual.blocks.11.attn.qkv", |
| "thinker.visual.blocks.11.attn.proj", |
| "thinker.visual.blocks.11.mlp.linear_fc1", |
| "thinker.visual.blocks.11.mlp.linear_fc2", |
| "thinker.visual.blocks.12.attn.qkv", |
| "thinker.visual.blocks.12.attn.proj", |
| "thinker.visual.blocks.12.mlp.linear_fc1", |
| "thinker.visual.blocks.12.mlp.linear_fc2", |
| "thinker.visual.blocks.13.attn.qkv", |
| "thinker.visual.blocks.13.attn.proj", |
| "thinker.visual.blocks.13.mlp.linear_fc1", |
| "thinker.visual.blocks.13.mlp.linear_fc2", |
| "thinker.visual.blocks.14.attn.qkv", |
| "thinker.visual.blocks.14.attn.proj", |
| "thinker.visual.blocks.14.mlp.linear_fc1", |
| "thinker.visual.blocks.14.mlp.linear_fc2", |
| "thinker.visual.blocks.15.attn.qkv", |
| "thinker.visual.blocks.15.attn.proj", |
| "thinker.visual.blocks.15.mlp.linear_fc1", |
| "thinker.visual.blocks.15.mlp.linear_fc2", |
| "thinker.visual.blocks.16.attn.qkv", |
| "thinker.visual.blocks.16.attn.proj", |
| "thinker.visual.blocks.16.mlp.linear_fc1", |
| "thinker.visual.blocks.16.mlp.linear_fc2", |
| "thinker.visual.blocks.17.attn.qkv", |
| "thinker.visual.blocks.17.attn.proj", |
| "thinker.visual.blocks.17.mlp.linear_fc1", |
| "thinker.visual.blocks.17.mlp.linear_fc2", |
| "thinker.visual.blocks.18.attn.qkv", |
| "thinker.visual.blocks.18.attn.proj", |
| "thinker.visual.blocks.18.mlp.linear_fc1", |
| "thinker.visual.blocks.18.mlp.linear_fc2", |
| "thinker.visual.blocks.19.attn.qkv", |
| "thinker.visual.blocks.19.attn.proj", |
| "thinker.visual.blocks.19.mlp.linear_fc1", |
| "thinker.visual.blocks.19.mlp.linear_fc2", |
| "thinker.visual.blocks.20.attn.qkv", |
| "thinker.visual.blocks.20.attn.proj", |
| "thinker.visual.blocks.20.mlp.linear_fc1", |
| "thinker.visual.blocks.20.mlp.linear_fc2", |
| "thinker.visual.blocks.21.attn.qkv", |
| "thinker.visual.blocks.21.attn.proj", |
| "thinker.visual.blocks.21.mlp.linear_fc1", |
| "thinker.visual.blocks.21.mlp.linear_fc2", |
| "thinker.visual.blocks.22.attn.qkv", |
| "thinker.visual.blocks.22.attn.proj", |
| "thinker.visual.blocks.22.mlp.linear_fc1", |
| "thinker.visual.blocks.22.mlp.linear_fc2", |
| "thinker.visual.blocks.23.attn.qkv", |
| "thinker.visual.blocks.23.attn.proj", |
| "thinker.visual.blocks.23.mlp.linear_fc1", |
| "thinker.visual.blocks.23.mlp.linear_fc2", |
| "thinker.visual.blocks.24.attn.qkv", |
| "thinker.visual.blocks.24.attn.proj", |
| "thinker.visual.blocks.24.mlp.linear_fc1", |
| "thinker.visual.blocks.24.mlp.linear_fc2", |
| "thinker.visual.blocks.25.attn.qkv", |
| "thinker.visual.blocks.25.attn.proj", |
| "thinker.visual.blocks.25.mlp.linear_fc1", |
| "thinker.visual.blocks.25.mlp.linear_fc2", |
| "thinker.visual.blocks.26.attn.qkv", |
| "thinker.visual.blocks.26.attn.proj", |
| "thinker.visual.blocks.26.mlp.linear_fc1", |
| "thinker.visual.blocks.26.mlp.linear_fc2", |
| "thinker.visual.merger.mlp.0", |
| "thinker.visual.merger.mlp.2", |
| "thinker.model.layers.0.mlp.gate", |
| "thinker.model.layers.1.mlp.gate", |
| "thinker.model.layers.2.mlp.gate", |
| "thinker.model.layers.3.mlp.gate", |
| "thinker.model.layers.4.mlp.gate", |
| "thinker.model.layers.5.mlp.gate", |
| "thinker.model.layers.6.mlp.gate", |
| "thinker.model.layers.7.mlp.gate", |
| "thinker.model.layers.8.mlp.gate", |
| "thinker.model.layers.9.mlp.gate", |
| "thinker.model.layers.10.mlp.gate", |
| "thinker.model.layers.11.mlp.gate", |
| "thinker.model.layers.12.mlp.gate", |
| "thinker.model.layers.13.mlp.gate", |
| "thinker.model.layers.14.mlp.gate", |
| "thinker.model.layers.15.mlp.gate", |
| "thinker.model.layers.16.mlp.gate", |
| "thinker.model.layers.17.mlp.gate", |
| "thinker.model.layers.18.mlp.gate", |
| "thinker.model.layers.19.mlp.gate", |
| "thinker.model.layers.20.mlp.gate", |
| "thinker.model.layers.21.mlp.gate", |
| "thinker.model.layers.22.mlp.gate", |
| "thinker.model.layers.23.mlp.gate", |
| "thinker.model.layers.24.mlp.gate", |
| "thinker.model.layers.25.mlp.gate", |
| "thinker.model.layers.26.mlp.gate", |
| "thinker.model.layers.27.mlp.gate", |
| "thinker.model.layers.28.mlp.gate", |
| "thinker.model.layers.29.mlp.gate", |
| "thinker.model.layers.30.mlp.gate", |
| "thinker.model.layers.31.mlp.gate", |
| "thinker.model.layers.32.mlp.gate", |
| "thinker.model.layers.33.mlp.gate", |
| "thinker.model.layers.34.mlp.gate", |
| "thinker.model.layers.35.mlp.gate", |
| "thinker.model.layers.36.mlp.gate", |
| "thinker.model.layers.37.mlp.gate", |
| "thinker.model.layers.38.mlp.gate", |
| "thinker.model.layers.39.mlp.gate", |
| "thinker.model.layers.40.mlp.gate", |
| "thinker.model.layers.41.mlp.gate", |
| "thinker.model.layers.42.mlp.gate", |
| "thinker.model.layers.43.mlp.gate", |
| "thinker.model.layers.44.mlp.gate", |
| "thinker.model.layers.45.mlp.gate", |
| "thinker.model.layers.46.mlp.gate", |
| "thinker.model.layers.47.mlp.gate", |
| "thinker.lm_head" |
| ], |
| "quant_analyse": false, |
| "quant_vit": false |
| }, |
| "cache": null |
| }, |
| "dataset_config": null, |
| "global_config": { |
| "save_path": "Save Model Path", |
| "max_seq_length": 2048, |
| "hidden_size": 2048, |
| "model_arch_type": "qwen3_omni_moe", |
| "absolute_model_path": "/home/lengyue/.cache/huggingface/hub/models--openaudio--qwen3-omni-30b-a3b-flash-fish-asr-20251224-e368-rl-e371-step50/snapshots/80027a9400ea73e1a5fd0f999ff5b1ce2615ad16", |
| "deploy_backend": "vllm" |
| }, |
| "infer_config": null, |
| "debug_info": { |
| "python": "3.12.11 | packaged by Anaconda, Inc. | (main, Jun 5 2025, 13:09:17) [GCC 11.2.0]", |
| "angelslim": { |
| "name": "angelslim", |
| "version": "0.2.2", |
| "source": "pip" |
| }, |
| "torch": { |
| "name": "torch", |
| "version": "2.8.0+cu128", |
| "source": "pip" |
| }, |
| "transformers": { |
| "name": "transformers", |
| "version": "4.57.1", |
| "source": "pip" |
| }, |
| "torch_cuda_version": "12.8" |
| } |
| } |