| { | |
| "architectures": [ | |
| "GlmImageForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_end_token_id": 16385, | |
| "image_start_token_id": 16384, | |
| "image_token_id": 167855, | |
| "model_type": "glm_image", | |
| "quantization_config": { | |
| "add_skip_keys": false, | |
| "dequantize_fp32": false, | |
| "dynamic_loss_threshold": 0.01, | |
| "group_size": 0, | |
| "is_integer": true, | |
| "is_training": false, | |
| "modules_dtype_dict": { | |
| "int5": [ | |
| "model.language_model.layers.28.self_attn.v_proj.weight", | |
| "model.language_model.layers.29.self_attn.v_proj.weight", | |
| "model.language_model.layers.32.self_attn.v_proj.weight", | |
| "model.language_model.layers.33.self_attn.v_proj.weight", | |
| "model.visual.blocks.0.attn.qkv.weight", | |
| "model.visual.blocks.0.mlp.fc2.weight", | |
| "model.visual.blocks.1.attn.qkv.weight", | |
| "model.visual.blocks.1.mlp.fc1.weight", | |
| "model.visual.blocks.1.mlp.fc2.weight", | |
| "model.visual.blocks.2.attn.qkv.weight", | |
| "model.visual.blocks.2.mlp.fc2.weight", | |
| "model.visual.blocks.3.attn.qkv.weight", | |
| "model.visual.blocks.3.mlp.fc2.weight", | |
| "model.visual.blocks.4.mlp.fc2.weight", | |
| "model.visual.blocks.5.mlp.fc2.weight", | |
| "model.visual.blocks.6.mlp.fc2.weight", | |
| "model.visual.blocks.7.mlp.fc2.weight", | |
| "model.visual.blocks.8.mlp.fc2.weight", | |
| "model.visual.blocks.9.mlp.fc2.weight" | |
| ], | |
| "uint4": [ | |
| "model.language_model.layers.0.mlp.down_proj.weight", | |
| "model.language_model.layers.0.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.0.self_attn.k_proj.weight", | |
| "model.language_model.layers.0.self_attn.o_proj.weight", | |
| "model.language_model.layers.0.self_attn.q_proj.weight", | |
| "model.language_model.layers.0.self_attn.v_proj.weight", | |
| "model.language_model.layers.1.mlp.down_proj.weight", | |
| "model.language_model.layers.1.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.1.self_attn.k_proj.weight", | |
| "model.language_model.layers.1.self_attn.o_proj.weight", | |
| "model.language_model.layers.1.self_attn.q_proj.weight", | |
| "model.language_model.layers.1.self_attn.v_proj.weight", | |
| "model.language_model.layers.2.mlp.down_proj.weight", | |
| "model.language_model.layers.2.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.2.self_attn.k_proj.weight", | |
| "model.language_model.layers.2.self_attn.o_proj.weight", | |
| "model.language_model.layers.2.self_attn.q_proj.weight", | |
| "model.language_model.layers.2.self_attn.v_proj.weight", | |
| "model.language_model.layers.3.mlp.down_proj.weight", | |
| "model.language_model.layers.3.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.3.self_attn.k_proj.weight", | |
| "model.language_model.layers.3.self_attn.o_proj.weight", | |
| "model.language_model.layers.3.self_attn.q_proj.weight", | |
| "model.language_model.layers.3.self_attn.v_proj.weight", | |
| "model.language_model.layers.4.mlp.down_proj.weight", | |
| "model.language_model.layers.4.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.4.self_attn.k_proj.weight", | |
| "model.language_model.layers.4.self_attn.o_proj.weight", | |
| "model.language_model.layers.4.self_attn.q_proj.weight", | |
| "model.language_model.layers.4.self_attn.v_proj.weight", | |
| "model.language_model.layers.5.mlp.down_proj.weight", | |
| "model.language_model.layers.5.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.5.self_attn.k_proj.weight", | |
| "model.language_model.layers.5.self_attn.o_proj.weight", | |
| "model.language_model.layers.5.self_attn.q_proj.weight", | |
| "model.language_model.layers.5.self_attn.v_proj.weight", | |
| "model.language_model.layers.6.mlp.down_proj.weight", | |
| "model.language_model.layers.6.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.6.self_attn.k_proj.weight", | |
| "model.language_model.layers.6.self_attn.o_proj.weight", | |
| "model.language_model.layers.6.self_attn.q_proj.weight", | |
| "model.language_model.layers.6.self_attn.v_proj.weight", | |
| "model.language_model.layers.7.mlp.down_proj.weight", | |
| "model.language_model.layers.7.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.7.self_attn.k_proj.weight", | |
| "model.language_model.layers.7.self_attn.o_proj.weight", | |
| "model.language_model.layers.7.self_attn.q_proj.weight", | |
| "model.language_model.layers.7.self_attn.v_proj.weight", | |
| "model.language_model.layers.8.mlp.down_proj.weight", | |
| "model.language_model.layers.8.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.8.self_attn.k_proj.weight", | |
| "model.language_model.layers.8.self_attn.o_proj.weight", | |
| "model.language_model.layers.8.self_attn.q_proj.weight", | |
| "model.language_model.layers.8.self_attn.v_proj.weight", | |
| "model.language_model.layers.9.mlp.down_proj.weight", | |
| "model.language_model.layers.9.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.9.self_attn.k_proj.weight", | |
| "model.language_model.layers.9.self_attn.o_proj.weight", | |
| "model.language_model.layers.9.self_attn.q_proj.weight", | |
| "model.language_model.layers.9.self_attn.v_proj.weight", | |
| "model.language_model.layers.10.mlp.down_proj.weight", | |
| "model.language_model.layers.10.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.10.self_attn.k_proj.weight", | |
| "model.language_model.layers.10.self_attn.o_proj.weight", | |
| "model.language_model.layers.10.self_attn.q_proj.weight", | |
| "model.language_model.layers.10.self_attn.v_proj.weight", | |
| "model.language_model.layers.11.mlp.down_proj.weight", | |
| "model.language_model.layers.11.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.11.self_attn.k_proj.weight", | |
| "model.language_model.layers.11.self_attn.o_proj.weight", | |
| "model.language_model.layers.11.self_attn.q_proj.weight", | |
| "model.language_model.layers.11.self_attn.v_proj.weight", | |
| "model.language_model.layers.12.mlp.down_proj.weight", | |
| "model.language_model.layers.12.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.12.self_attn.k_proj.weight", | |
| "model.language_model.layers.12.self_attn.o_proj.weight", | |
| "model.language_model.layers.12.self_attn.q_proj.weight", | |
| "model.language_model.layers.12.self_attn.v_proj.weight", | |
| "model.language_model.layers.13.mlp.down_proj.weight", | |
| "model.language_model.layers.13.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.13.self_attn.k_proj.weight", | |
| "model.language_model.layers.13.self_attn.o_proj.weight", | |
| "model.language_model.layers.13.self_attn.q_proj.weight", | |
| "model.language_model.layers.13.self_attn.v_proj.weight", | |
| "model.language_model.layers.14.mlp.down_proj.weight", | |
| "model.language_model.layers.14.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.14.self_attn.k_proj.weight", | |
| "model.language_model.layers.14.self_attn.o_proj.weight", | |
| "model.language_model.layers.14.self_attn.q_proj.weight", | |
| "model.language_model.layers.14.self_attn.v_proj.weight", | |
| "model.language_model.layers.15.mlp.down_proj.weight", | |
| "model.language_model.layers.15.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.15.self_attn.k_proj.weight", | |
| "model.language_model.layers.15.self_attn.o_proj.weight", | |
| "model.language_model.layers.15.self_attn.q_proj.weight", | |
| "model.language_model.layers.15.self_attn.v_proj.weight", | |
| "model.language_model.layers.16.mlp.down_proj.weight", | |
| "model.language_model.layers.16.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.16.self_attn.k_proj.weight", | |
| "model.language_model.layers.16.self_attn.o_proj.weight", | |
| "model.language_model.layers.16.self_attn.q_proj.weight", | |
| "model.language_model.layers.16.self_attn.v_proj.weight", | |
| "model.language_model.layers.17.mlp.down_proj.weight", | |
| "model.language_model.layers.17.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.17.self_attn.k_proj.weight", | |
| "model.language_model.layers.17.self_attn.o_proj.weight", | |
| "model.language_model.layers.17.self_attn.q_proj.weight", | |
| "model.language_model.layers.17.self_attn.v_proj.weight", | |
| "model.language_model.layers.18.mlp.down_proj.weight", | |
| "model.language_model.layers.18.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.18.self_attn.k_proj.weight", | |
| "model.language_model.layers.18.self_attn.o_proj.weight", | |
| "model.language_model.layers.18.self_attn.q_proj.weight", | |
| "model.language_model.layers.18.self_attn.v_proj.weight", | |
| "model.language_model.layers.19.mlp.down_proj.weight", | |
| "model.language_model.layers.19.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.19.self_attn.k_proj.weight", | |
| "model.language_model.layers.19.self_attn.o_proj.weight", | |
| "model.language_model.layers.19.self_attn.q_proj.weight", | |
| "model.language_model.layers.19.self_attn.v_proj.weight", | |
| "model.language_model.layers.20.mlp.down_proj.weight", | |
| "model.language_model.layers.20.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.20.self_attn.k_proj.weight", | |
| "model.language_model.layers.20.self_attn.o_proj.weight", | |
| "model.language_model.layers.20.self_attn.q_proj.weight", | |
| "model.language_model.layers.20.self_attn.v_proj.weight", | |
| "model.language_model.layers.21.mlp.down_proj.weight", | |
| "model.language_model.layers.21.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.21.self_attn.k_proj.weight", | |
| "model.language_model.layers.21.self_attn.o_proj.weight", | |
| "model.language_model.layers.21.self_attn.q_proj.weight", | |
| "model.language_model.layers.21.self_attn.v_proj.weight", | |
| "model.language_model.layers.22.mlp.down_proj.weight", | |
| "model.language_model.layers.22.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.22.self_attn.k_proj.weight", | |
| "model.language_model.layers.22.self_attn.o_proj.weight", | |
| "model.language_model.layers.22.self_attn.q_proj.weight", | |
| "model.language_model.layers.22.self_attn.v_proj.weight", | |
| "model.language_model.layers.23.mlp.down_proj.weight", | |
| "model.language_model.layers.23.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.23.self_attn.k_proj.weight", | |
| "model.language_model.layers.23.self_attn.o_proj.weight", | |
| "model.language_model.layers.23.self_attn.q_proj.weight", | |
| "model.language_model.layers.23.self_attn.v_proj.weight", | |
| "model.language_model.layers.24.mlp.down_proj.weight", | |
| "model.language_model.layers.24.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.24.self_attn.k_proj.weight", | |
| "model.language_model.layers.24.self_attn.o_proj.weight", | |
| "model.language_model.layers.24.self_attn.q_proj.weight", | |
| "model.language_model.layers.24.self_attn.v_proj.weight", | |
| "model.language_model.layers.25.mlp.down_proj.weight", | |
| "model.language_model.layers.25.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.25.self_attn.k_proj.weight", | |
| "model.language_model.layers.25.self_attn.o_proj.weight", | |
| "model.language_model.layers.25.self_attn.q_proj.weight", | |
| "model.language_model.layers.25.self_attn.v_proj.weight", | |
| "model.language_model.layers.26.mlp.down_proj.weight", | |
| "model.language_model.layers.26.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.26.self_attn.k_proj.weight", | |
| "model.language_model.layers.26.self_attn.o_proj.weight", | |
| "model.language_model.layers.26.self_attn.q_proj.weight", | |
| "model.language_model.layers.26.self_attn.v_proj.weight", | |
| "model.language_model.layers.27.mlp.down_proj.weight", | |
| "model.language_model.layers.27.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.27.self_attn.k_proj.weight", | |
| "model.language_model.layers.27.self_attn.o_proj.weight", | |
| "model.language_model.layers.27.self_attn.q_proj.weight", | |
| "model.language_model.layers.27.self_attn.v_proj.weight", | |
| "model.language_model.layers.28.mlp.down_proj.weight", | |
| "model.language_model.layers.28.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.28.self_attn.k_proj.weight", | |
| "model.language_model.layers.28.self_attn.o_proj.weight", | |
| "model.language_model.layers.28.self_attn.q_proj.weight", | |
| "model.language_model.layers.29.mlp.down_proj.weight", | |
| "model.language_model.layers.29.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.29.self_attn.k_proj.weight", | |
| "model.language_model.layers.29.self_attn.o_proj.weight", | |
| "model.language_model.layers.29.self_attn.q_proj.weight", | |
| "model.language_model.layers.30.mlp.down_proj.weight", | |
| "model.language_model.layers.30.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.30.self_attn.k_proj.weight", | |
| "model.language_model.layers.30.self_attn.o_proj.weight", | |
| "model.language_model.layers.30.self_attn.q_proj.weight", | |
| "model.language_model.layers.30.self_attn.v_proj.weight", | |
| "model.language_model.layers.31.mlp.down_proj.weight", | |
| "model.language_model.layers.31.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.31.self_attn.k_proj.weight", | |
| "model.language_model.layers.31.self_attn.o_proj.weight", | |
| "model.language_model.layers.31.self_attn.q_proj.weight", | |
| "model.language_model.layers.31.self_attn.v_proj.weight", | |
| "model.language_model.layers.32.mlp.down_proj.weight", | |
| "model.language_model.layers.32.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.32.self_attn.k_proj.weight", | |
| "model.language_model.layers.32.self_attn.o_proj.weight", | |
| "model.language_model.layers.32.self_attn.q_proj.weight", | |
| "model.language_model.layers.33.mlp.down_proj.weight", | |
| "model.language_model.layers.33.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.33.self_attn.k_proj.weight", | |
| "model.language_model.layers.33.self_attn.o_proj.weight", | |
| "model.language_model.layers.33.self_attn.q_proj.weight", | |
| "model.language_model.layers.34.mlp.down_proj.weight", | |
| "model.language_model.layers.34.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.34.self_attn.k_proj.weight", | |
| "model.language_model.layers.34.self_attn.o_proj.weight", | |
| "model.language_model.layers.34.self_attn.q_proj.weight", | |
| "model.language_model.layers.34.self_attn.v_proj.weight", | |
| "model.language_model.layers.35.mlp.down_proj.weight", | |
| "model.language_model.layers.35.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.35.self_attn.k_proj.weight", | |
| "model.language_model.layers.35.self_attn.o_proj.weight", | |
| "model.language_model.layers.35.self_attn.q_proj.weight", | |
| "model.language_model.layers.35.self_attn.v_proj.weight", | |
| "model.language_model.layers.36.mlp.down_proj.weight", | |
| "model.language_model.layers.36.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.36.self_attn.k_proj.weight", | |
| "model.language_model.layers.36.self_attn.o_proj.weight", | |
| "model.language_model.layers.36.self_attn.q_proj.weight", | |
| "model.language_model.layers.36.self_attn.v_proj.weight", | |
| "model.language_model.layers.37.mlp.down_proj.weight", | |
| "model.language_model.layers.37.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.37.self_attn.k_proj.weight", | |
| "model.language_model.layers.37.self_attn.o_proj.weight", | |
| "model.language_model.layers.37.self_attn.q_proj.weight", | |
| "model.language_model.layers.37.self_attn.v_proj.weight", | |
| "model.language_model.layers.38.mlp.down_proj.weight", | |
| "model.language_model.layers.38.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.38.self_attn.k_proj.weight", | |
| "model.language_model.layers.38.self_attn.o_proj.weight", | |
| "model.language_model.layers.38.self_attn.q_proj.weight", | |
| "model.language_model.layers.38.self_attn.v_proj.weight", | |
| "model.language_model.layers.39.mlp.down_proj.weight", | |
| "model.language_model.layers.39.mlp.gate_up_proj.weight", | |
| "model.language_model.layers.39.self_attn.k_proj.weight", | |
| "model.language_model.layers.39.self_attn.o_proj.weight", | |
| "model.language_model.layers.39.self_attn.q_proj.weight", | |
| "model.language_model.layers.39.self_attn.v_proj.weight", | |
| "model.visual.blocks.0.attn.proj.weight", | |
| "model.visual.blocks.0.mlp.fc1.weight", | |
| "model.visual.blocks.1.attn.proj.weight", | |
| "model.visual.blocks.2.attn.proj.weight", | |
| "model.visual.blocks.2.mlp.fc1.weight", | |
| "model.visual.blocks.3.attn.proj.weight", | |
| "model.visual.blocks.3.mlp.fc1.weight", | |
| "model.visual.blocks.4.attn.proj.weight", | |
| "model.visual.blocks.4.attn.qkv.weight", | |
| "model.visual.blocks.4.mlp.fc1.weight", | |
| "model.visual.blocks.5.attn.proj.weight", | |
| "model.visual.blocks.5.attn.qkv.weight", | |
| "model.visual.blocks.5.mlp.fc1.weight", | |
| "model.visual.blocks.6.attn.proj.weight", | |
| "model.visual.blocks.6.attn.qkv.weight", | |
| "model.visual.blocks.6.mlp.fc1.weight", | |
| "model.visual.blocks.7.attn.proj.weight", | |
| "model.visual.blocks.7.attn.qkv.weight", | |
| "model.visual.blocks.7.mlp.fc1.weight", | |
| "model.visual.blocks.8.attn.proj.weight", | |
| "model.visual.blocks.8.attn.qkv.weight", | |
| "model.visual.blocks.8.mlp.fc1.weight", | |
| "model.visual.blocks.9.attn.proj.weight", | |
| "model.visual.blocks.9.attn.qkv.weight", | |
| "model.visual.blocks.9.mlp.fc1.weight", | |
| "model.visual.blocks.10.attn.proj.weight", | |
| "model.visual.blocks.10.attn.qkv.weight", | |
| "model.visual.blocks.10.mlp.fc1.weight", | |
| "model.visual.blocks.10.mlp.fc2.weight", | |
| "model.visual.blocks.11.attn.proj.weight", | |
| "model.visual.blocks.11.attn.qkv.weight", | |
| "model.visual.blocks.11.mlp.fc1.weight", | |
| "model.visual.blocks.11.mlp.fc2.weight", | |
| "model.visual.blocks.12.attn.proj.weight", | |
| "model.visual.blocks.12.attn.qkv.weight", | |
| "model.visual.blocks.12.mlp.fc1.weight", | |
| "model.visual.blocks.12.mlp.fc2.weight", | |
| "model.visual.blocks.13.attn.proj.weight", | |
| "model.visual.blocks.13.attn.qkv.weight", | |
| "model.visual.blocks.13.mlp.fc1.weight", | |
| "model.visual.blocks.13.mlp.fc2.weight", | |
| "model.visual.blocks.14.attn.proj.weight", | |
| "model.visual.blocks.14.attn.qkv.weight", | |
| "model.visual.blocks.14.mlp.fc1.weight", | |
| "model.visual.blocks.14.mlp.fc2.weight", | |
| "model.visual.blocks.15.attn.proj.weight", | |
| "model.visual.blocks.15.attn.qkv.weight", | |
| "model.visual.blocks.15.mlp.fc1.weight", | |
| "model.visual.blocks.15.mlp.fc2.weight", | |
| "model.visual.blocks.16.attn.proj.weight", | |
| "model.visual.blocks.16.attn.qkv.weight", | |
| "model.visual.blocks.16.mlp.fc1.weight", | |
| "model.visual.blocks.16.mlp.fc2.weight", | |
| "model.visual.blocks.17.attn.proj.weight", | |
| "model.visual.blocks.17.attn.qkv.weight", | |
| "model.visual.blocks.17.mlp.fc1.weight", | |
| "model.visual.blocks.17.mlp.fc2.weight", | |
| "model.visual.blocks.18.attn.proj.weight", | |
| "model.visual.blocks.18.attn.qkv.weight", | |
| "model.visual.blocks.18.mlp.fc1.weight", | |
| "model.visual.blocks.18.mlp.fc2.weight", | |
| "model.visual.blocks.19.attn.proj.weight", | |
| "model.visual.blocks.19.attn.qkv.weight", | |
| "model.visual.blocks.19.mlp.fc1.weight", | |
| "model.visual.blocks.19.mlp.fc2.weight", | |
| "model.visual.blocks.20.attn.proj.weight", | |
| "model.visual.blocks.20.attn.qkv.weight", | |
| "model.visual.blocks.20.mlp.fc1.weight", | |
| "model.visual.blocks.20.mlp.fc2.weight", | |
| "model.visual.blocks.21.attn.proj.weight", | |
| "model.visual.blocks.21.attn.qkv.weight", | |
| "model.visual.blocks.21.mlp.fc1.weight", | |
| "model.visual.blocks.21.mlp.fc2.weight", | |
| "model.visual.blocks.22.attn.proj.weight", | |
| "model.visual.blocks.22.attn.qkv.weight", | |
| "model.visual.blocks.22.mlp.fc1.weight", | |
| "model.visual.blocks.22.mlp.fc2.weight", | |
| "model.visual.blocks.23.attn.proj.weight", | |
| "model.visual.blocks.23.attn.qkv.weight", | |
| "model.visual.blocks.23.mlp.fc1.weight", | |
| "model.visual.blocks.23.mlp.fc2.weight", | |
| "model.visual.blocks.24.attn.proj.weight", | |
| "model.visual.blocks.24.attn.qkv.weight", | |
| "model.visual.blocks.24.mlp.fc1.weight", | |
| "model.visual.blocks.24.mlp.fc2.weight", | |
| "model.visual.blocks.25.attn.proj.weight", | |
| "model.visual.blocks.25.attn.qkv.weight", | |
| "model.visual.blocks.25.mlp.fc1.weight", | |
| "model.visual.blocks.25.mlp.fc2.weight", | |
| "model.visual.blocks.26.attn.proj.weight", | |
| "model.visual.blocks.26.attn.qkv.weight", | |
| "model.visual.blocks.26.mlp.fc1.weight", | |
| "model.visual.blocks.26.mlp.fc2.weight", | |
| "model.visual.blocks.27.attn.proj.weight", | |
| "model.visual.blocks.27.attn.qkv.weight", | |
| "model.visual.blocks.27.mlp.fc1.weight", | |
| "model.visual.blocks.27.mlp.fc2.weight", | |
| "model.visual.blocks.28.attn.proj.weight", | |
| "model.visual.blocks.28.attn.qkv.weight", | |
| "model.visual.blocks.28.mlp.fc1.weight", | |
| "model.visual.blocks.28.mlp.fc2.weight", | |
| "model.visual.blocks.29.attn.proj.weight", | |
| "model.visual.blocks.29.attn.qkv.weight", | |
| "model.visual.blocks.29.mlp.fc1.weight", | |
| "model.visual.blocks.29.mlp.fc2.weight", | |
| "model.visual.blocks.30.attn.proj.weight", | |
| "model.visual.blocks.30.attn.qkv.weight", | |
| "model.visual.blocks.30.mlp.fc1.weight", | |
| "model.visual.blocks.30.mlp.fc2.weight", | |
| "model.visual.blocks.31.attn.proj.weight", | |
| "model.visual.blocks.31.attn.qkv.weight", | |
| "model.visual.blocks.31.mlp.fc1.weight", | |
| "model.visual.blocks.31.mlp.fc2.weight", | |
| "model.visual.blocks.32.attn.proj.weight", | |
| "model.visual.blocks.32.attn.qkv.weight", | |
| "model.visual.blocks.32.mlp.fc1.weight", | |
| "model.visual.blocks.32.mlp.fc2.weight", | |
| "model.visual.blocks.33.attn.proj.weight", | |
| "model.visual.blocks.33.attn.qkv.weight", | |
| "model.visual.blocks.33.mlp.fc1.weight", | |
| "model.visual.blocks.33.mlp.fc2.weight", | |
| "model.visual.blocks.34.attn.proj.weight", | |
| "model.visual.blocks.34.attn.qkv.weight", | |
| "model.visual.blocks.34.mlp.fc1.weight", | |
| "model.visual.blocks.34.mlp.fc2.weight", | |
| "model.visual.blocks.35.attn.proj.weight", | |
| "model.visual.blocks.35.attn.qkv.weight", | |
| "model.visual.blocks.35.mlp.fc1.weight", | |
| "model.visual.blocks.35.mlp.fc2.weight", | |
| "model.visual.blocks.36.attn.proj.weight", | |
| "model.visual.blocks.36.attn.qkv.weight", | |
| "model.visual.blocks.36.mlp.fc1.weight", | |
| "model.visual.blocks.36.mlp.fc2.weight", | |
| "model.visual.blocks.37.attn.proj.weight", | |
| "model.visual.blocks.37.attn.qkv.weight", | |
| "model.visual.blocks.37.mlp.fc1.weight", | |
| "model.visual.blocks.37.mlp.fc2.weight", | |
| "model.visual.blocks.38.attn.proj.weight", | |
| "model.visual.blocks.38.attn.qkv.weight", | |
| "model.visual.blocks.38.mlp.fc1.weight", | |
| "model.visual.blocks.38.mlp.fc2.weight", | |
| "model.visual.blocks.39.attn.proj.weight", | |
| "model.visual.blocks.39.attn.qkv.weight", | |
| "model.visual.blocks.39.mlp.fc1.weight", | |
| "model.visual.blocks.39.mlp.fc2.weight" | |
| ] | |
| }, | |
| "modules_to_not_convert": [ | |
| "vqmodel", | |
| "lm_head", | |
| "embeddings", | |
| "embed_tokens", | |
| "patch_embed" | |
| ], | |
| "non_blocking": false, | |
| "quant_conv": false, | |
| "quant_method": "sdnq", | |
| "quantization_device": null, | |
| "quantized_matmul_dtype": null, | |
| "return_device": null, | |
| "sdnq_version": "0.1.4", | |
| "svd_rank": 32, | |
| "svd_steps": 8, | |
| "use_dynamic_quantization": true, | |
| "use_grad_ckpt": true, | |
| "use_quantized_matmul": false, | |
| "use_quantized_matmul_conv": false, | |
| "use_static_quantization": true, | |
| "use_stochastic_rounding": false, | |
| "use_svd": false, | |
| "weights_dtype": "uint4" | |
| }, | |
| "text_config": { | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 16385, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13696, | |
| "max_position_embeddings": 131072, | |
| "model_type": "glm_image_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 167841, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "mrope_section": [ | |
| 8, | |
| 12, | |
| 12 | |
| ], | |
| "partial_rotary_factor": 0.5, | |
| "rope_theta": 10000, | |
| "rope_type": "default" | |
| }, | |
| "use_cache": true, | |
| "vision_vocab_size": 16512, | |
| "vocab_size": 168064 | |
| }, | |
| "transformers_version": "5.0.0.dev0", | |
| "vision_config": { | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "depth": 40, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu", | |
| "hidden_size": 1536, | |
| "image_size": 2048, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "glm_image_vision", | |
| "num_heads": 16, | |
| "patch_size": 16, | |
| "spatial_merge_size": 1 | |
| }, | |
| "vq_config": { | |
| "dtype": "bfloat16", | |
| "embed_dim": 2048, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "latent_channels": 1536, | |
| "model_type": "glm_image_vqmodel", | |
| "num_embeddings": 16384 | |
| } | |
| } | |