| { | |
| "architectures": [ | |
| "Gemma3ForConditionalGeneration" | |
| ], | |
| "boi_token_index": 255999, | |
| "dtype": "bfloat16", | |
| "eoi_token_index": 256000, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "image_token_index": 262144, | |
| "initializer_range": 0.02, | |
| "mm_tokens_per_image": 256, | |
| "model_type": "gemma3", | |
| "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.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight", | |
| "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight", | |
| "model.language_model.layers.17.self_attn.k_proj.weight" | |
| ], | |
| "uint4": [ | |
| "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight", | |
| "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight", | |
| "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight", | |
| "model.language_model.layers.0.mlp.down_proj.weight", | |
| "model.language_model.layers.0.mlp.gate_proj.weight", | |
| "model.language_model.layers.0.mlp.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.self_attn.q_proj.weight", | |
| "model.language_model.layers.1.mlp.down_proj.weight", | |
| "model.language_model.layers.1.mlp.gate_proj.weight", | |
| "model.language_model.layers.1.mlp.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.v_proj.weight", | |
| "model.language_model.layers.2.mlp.down_proj.weight", | |
| "model.language_model.layers.2.mlp.gate_proj.weight", | |
| "model.language_model.layers.2.mlp.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_proj.weight", | |
| "model.language_model.layers.3.mlp.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_proj.weight", | |
| "model.language_model.layers.4.mlp.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_proj.weight", | |
| "model.language_model.layers.5.mlp.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.gate_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.10.mlp.down_proj.weight", | |
| "model.language_model.layers.10.mlp.gate_proj.weight", | |
| "model.language_model.layers.10.mlp.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_proj.weight", | |
| "model.language_model.layers.11.mlp.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.6.mlp.down_proj.weight", | |
| "model.language_model.layers.6.mlp.up_proj.weight", | |
| "model.language_model.layers.7.mlp.down_proj.weight", | |
| "model.language_model.layers.7.mlp.gate_proj.weight", | |
| "model.language_model.layers.7.mlp.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_proj.weight", | |
| "model.language_model.layers.8.mlp.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_proj.weight", | |
| "model.language_model.layers.9.mlp.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.12.mlp.down_proj.weight", | |
| "model.language_model.layers.12.mlp.gate_proj.weight", | |
| "model.language_model.layers.12.mlp.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_proj.weight", | |
| "model.language_model.layers.13.mlp.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_proj.weight", | |
| "model.language_model.layers.14.mlp.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_proj.weight", | |
| "model.language_model.layers.15.mlp.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_proj.weight", | |
| "model.language_model.layers.16.mlp.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.gate_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.17.mlp.down_proj.weight", | |
| "model.language_model.layers.17.mlp.up_proj.weight", | |
| "model.language_model.layers.18.mlp.down_proj.weight", | |
| "model.language_model.layers.18.mlp.gate_proj.weight", | |
| "model.language_model.layers.18.mlp.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_proj.weight", | |
| "model.language_model.layers.19.mlp.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_proj.weight", | |
| "model.language_model.layers.20.mlp.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_proj.weight", | |
| "model.language_model.layers.21.mlp.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_proj.weight", | |
| "model.language_model.layers.22.mlp.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_proj.weight", | |
| "model.language_model.layers.23.mlp.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_proj.weight", | |
| "model.language_model.layers.24.mlp.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_proj.weight", | |
| "model.language_model.layers.25.mlp.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_proj.weight", | |
| "model.language_model.layers.26.mlp.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_proj.weight", | |
| "model.language_model.layers.27.mlp.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.gate_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.28.self_attn.v_proj.weight", | |
| "model.language_model.layers.28.mlp.down_proj.weight", | |
| "model.language_model.layers.28.mlp.up_proj.weight", | |
| "model.language_model.layers.29.mlp.down_proj.weight", | |
| "model.language_model.layers.29.mlp.gate_proj.weight", | |
| "model.language_model.layers.29.mlp.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.29.self_attn.v_proj.weight", | |
| "model.language_model.layers.30.mlp.down_proj.weight", | |
| "model.language_model.layers.30.mlp.gate_proj.weight", | |
| "model.language_model.layers.30.mlp.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_proj.weight", | |
| "model.language_model.layers.31.mlp.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_proj.weight", | |
| "model.language_model.layers.32.mlp.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.32.self_attn.v_proj.weight", | |
| "model.language_model.layers.33.mlp.down_proj.weight", | |
| "model.language_model.layers.33.mlp.gate_proj.weight", | |
| "model.language_model.layers.33.mlp.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.33.self_attn.v_proj.weight", | |
| "model.language_model.layers.34.mlp.down_proj.weight", | |
| "model.language_model.layers.34.mlp.gate_proj.weight", | |
| "model.language_model.layers.34.mlp.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_proj.weight", | |
| "model.language_model.layers.35.mlp.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_proj.weight", | |
| "model.language_model.layers.36.mlp.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_proj.weight", | |
| "model.language_model.layers.37.mlp.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_proj.weight", | |
| "model.language_model.layers.38.mlp.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.gate_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.language_model.layers.39.mlp.down_proj.weight", | |
| "model.language_model.layers.39.mlp.up_proj.weight", | |
| "model.language_model.layers.40.mlp.down_proj.weight", | |
| "model.language_model.layers.40.mlp.gate_proj.weight", | |
| "model.language_model.layers.40.mlp.up_proj.weight", | |
| "model.language_model.layers.40.self_attn.k_proj.weight", | |
| "model.language_model.layers.40.self_attn.o_proj.weight", | |
| "model.language_model.layers.40.self_attn.q_proj.weight", | |
| "model.language_model.layers.40.self_attn.v_proj.weight", | |
| "model.language_model.layers.41.mlp.down_proj.weight", | |
| "model.language_model.layers.41.mlp.gate_proj.weight", | |
| "model.language_model.layers.41.mlp.up_proj.weight", | |
| "model.language_model.layers.41.self_attn.k_proj.weight", | |
| "model.language_model.layers.41.self_attn.o_proj.weight", | |
| "model.language_model.layers.41.self_attn.q_proj.weight", | |
| "model.language_model.layers.41.self_attn.v_proj.weight", | |
| "model.language_model.layers.42.mlp.down_proj.weight", | |
| "model.language_model.layers.42.mlp.gate_proj.weight", | |
| "model.language_model.layers.42.mlp.up_proj.weight", | |
| "model.language_model.layers.42.self_attn.k_proj.weight", | |
| "model.language_model.layers.42.self_attn.o_proj.weight", | |
| "model.language_model.layers.42.self_attn.q_proj.weight", | |
| "model.language_model.layers.42.self_attn.v_proj.weight", | |
| "model.language_model.layers.43.mlp.down_proj.weight", | |
| "model.language_model.layers.43.mlp.gate_proj.weight", | |
| "model.language_model.layers.43.mlp.up_proj.weight", | |
| "model.language_model.layers.43.self_attn.k_proj.weight", | |
| "model.language_model.layers.43.self_attn.o_proj.weight", | |
| "model.language_model.layers.43.self_attn.q_proj.weight", | |
| "model.language_model.layers.43.self_attn.v_proj.weight", | |
| "model.language_model.layers.44.mlp.down_proj.weight", | |
| "model.language_model.layers.44.mlp.gate_proj.weight", | |
| "model.language_model.layers.44.mlp.up_proj.weight", | |
| "model.language_model.layers.44.self_attn.k_proj.weight", | |
| "model.language_model.layers.44.self_attn.o_proj.weight", | |
| "model.language_model.layers.44.self_attn.q_proj.weight", | |
| "model.language_model.layers.44.self_attn.v_proj.weight", | |
| "model.language_model.layers.45.mlp.down_proj.weight", | |
| "model.language_model.layers.45.mlp.gate_proj.weight", | |
| "model.language_model.layers.45.mlp.up_proj.weight", | |
| "model.language_model.layers.45.self_attn.k_proj.weight", | |
| "model.language_model.layers.45.self_attn.o_proj.weight", | |
| "model.language_model.layers.45.self_attn.q_proj.weight", | |
| "model.language_model.layers.45.self_attn.v_proj.weight", | |
| "model.language_model.layers.46.mlp.down_proj.weight", | |
| "model.language_model.layers.46.mlp.gate_proj.weight", | |
| "model.language_model.layers.46.mlp.up_proj.weight", | |
| "model.language_model.layers.46.self_attn.k_proj.weight", | |
| "model.language_model.layers.46.self_attn.o_proj.weight", | |
| "model.language_model.layers.46.self_attn.q_proj.weight", | |
| "model.language_model.layers.46.self_attn.v_proj.weight", | |
| "model.language_model.layers.47.mlp.down_proj.weight", | |
| "model.language_model.layers.47.mlp.gate_proj.weight", | |
| "model.language_model.layers.47.mlp.up_proj.weight", | |
| "model.language_model.layers.47.self_attn.k_proj.weight", | |
| "model.language_model.layers.47.self_attn.o_proj.weight", | |
| "model.language_model.layers.47.self_attn.q_proj.weight", | |
| "model.language_model.layers.47.self_attn.v_proj.weight" | |
| ] | |
| }, | |
| "modules_to_not_convert": [ | |
| ".condition_embedder", | |
| ".txt_out", | |
| "lm_head.weight", | |
| ".vid_out", | |
| ".emb_out", | |
| ".emb_in", | |
| "model.language_model.embed_tokens", | |
| "lm_head", | |
| ".img_out", | |
| ".t_embedder", | |
| ".norm_out", | |
| ".txt_in", | |
| "time_text_embed", | |
| ".context_embedder", | |
| ".y_embedder", | |
| "patch_emb", | |
| "wte", | |
| ".final_layer", | |
| ".img_in", | |
| ".x_embedder", | |
| "multi_modal_projector", | |
| "patch_embed", | |
| ".time_embed", | |
| "model.language_model.norm", | |
| ".vid_in", | |
| ".proj_out", | |
| "patch_embedding" | |
| ], | |
| "non_blocking": false, | |
| "quant_conv": false, | |
| "quant_method": "sdnq", | |
| "quantization_device": null, | |
| "quantized_matmul_dtype": "int8", | |
| "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": "int4" | |
| }, | |
| "text_config": { | |
| "_sliding_window_pattern": 6, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "cache_implementation": "hybrid", | |
| "dtype": "bfloat16", | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 3840, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 15360, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "rope_type": "linear" | |
| }, | |
| "rope_theta": 1000000, | |
| "sliding_window": 1024, | |
| "sliding_window_pattern": 6, | |
| "use_bidirectional_attention": false, | |
| "use_cache": true, | |
| "vocab_size": 262208 | |
| }, | |
| "transformers_version": "4.57.3", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 896, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14, | |
| "vision_use_head": false | |
| } | |
| } | |