{ "_name_or_path": "/home/shubhra/.cache/huggingface/hub/models--meta-llama--Llama-3.2-90B-Vision-Instruct/snapshots/0a6d69b1d745b4035898094f5d873978f88b235c", "architectures": [ "MllamaForConditionalGeneration" ], "image_token_index": 128256, "model_type": "mllama", "quantization_config": { "config_groups": { "group_0": { "input_activations": null, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "minmax", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" } } }, "format": "pack-quantized", "global_compression_ratio": 1.591378219604548, "ignore": [ "vision_model.transformer.layers.0.self_attn.q_proj", "vision_model.transformer.layers.0.self_attn.k_proj", "vision_model.transformer.layers.0.self_attn.v_proj", "vision_model.transformer.layers.0.self_attn.o_proj", "vision_model.transformer.layers.0.mlp.fc1", "vision_model.transformer.layers.0.mlp.fc2", "vision_model.transformer.layers.1.self_attn.q_proj", "vision_model.transformer.layers.1.self_attn.k_proj", "vision_model.transformer.layers.1.self_attn.v_proj", "vision_model.transformer.layers.1.self_attn.o_proj", "vision_model.transformer.layers.1.mlp.fc1", "vision_model.transformer.layers.1.mlp.fc2", "vision_model.transformer.layers.2.self_attn.q_proj", "vision_model.transformer.layers.2.self_attn.k_proj", "vision_model.transformer.layers.2.self_attn.v_proj", "vision_model.transformer.layers.2.self_attn.o_proj", "vision_model.transformer.layers.2.mlp.fc1", "vision_model.transformer.layers.2.mlp.fc2", "vision_model.transformer.layers.3.self_attn.q_proj", "vision_model.transformer.layers.3.self_attn.k_proj", "vision_model.transformer.layers.3.self_attn.v_proj", "vision_model.transformer.layers.3.self_attn.o_proj", "vision_model.transformer.layers.3.mlp.fc1", "vision_model.transformer.layers.3.mlp.fc2", "vision_model.transformer.layers.4.self_attn.q_proj", "vision_model.transformer.layers.4.self_attn.k_proj", "vision_model.transformer.layers.4.self_attn.v_proj", "vision_model.transformer.layers.4.self_attn.o_proj", "vision_model.transformer.layers.4.mlp.fc1", "vision_model.transformer.layers.4.mlp.fc2", "vision_model.transformer.layers.5.self_attn.q_proj", "vision_model.transformer.layers.5.self_attn.k_proj", "vision_model.transformer.layers.5.self_attn.v_proj", "vision_model.transformer.layers.5.self_attn.o_proj", "vision_model.transformer.layers.5.mlp.fc1", "vision_model.transformer.layers.5.mlp.fc2", "vision_model.transformer.layers.6.self_attn.q_proj", "vision_model.transformer.layers.6.self_attn.k_proj", "vision_model.transformer.layers.6.self_attn.v_proj", "vision_model.transformer.layers.6.self_attn.o_proj", "vision_model.transformer.layers.6.mlp.fc1", "vision_model.transformer.layers.6.mlp.fc2", "vision_model.transformer.layers.7.self_attn.q_proj", "vision_model.transformer.layers.7.self_attn.k_proj", "vision_model.transformer.layers.7.self_attn.v_proj", "vision_model.transformer.layers.7.self_attn.o_proj", "vision_model.transformer.layers.7.mlp.fc1", "vision_model.transformer.layers.7.mlp.fc2", "vision_model.transformer.layers.8.self_attn.q_proj", "vision_model.transformer.layers.8.self_attn.k_proj", "vision_model.transformer.layers.8.self_attn.v_proj", "vision_model.transformer.layers.8.self_attn.o_proj", "vision_model.transformer.layers.8.mlp.fc1", "vision_model.transformer.layers.8.mlp.fc2", "vision_model.transformer.layers.9.self_attn.q_proj", "vision_model.transformer.layers.9.self_attn.k_proj", "vision_model.transformer.layers.9.self_attn.v_proj", "vision_model.transformer.layers.9.self_attn.o_proj", "vision_model.transformer.layers.9.mlp.fc1", "vision_model.transformer.layers.9.mlp.fc2", "vision_model.transformer.layers.10.self_attn.q_proj", "vision_model.transformer.layers.10.self_attn.k_proj", "vision_model.transformer.layers.10.self_attn.v_proj", "vision_model.transformer.layers.10.self_attn.o_proj", "vision_model.transformer.layers.10.mlp.fc1", "vision_model.transformer.layers.10.mlp.fc2", "vision_model.transformer.layers.11.self_attn.q_proj", "vision_model.transformer.layers.11.self_attn.k_proj", "vision_model.transformer.layers.11.self_attn.v_proj", "vision_model.transformer.layers.11.self_attn.o_proj", "vision_model.transformer.layers.11.mlp.fc1", "vision_model.transformer.layers.11.mlp.fc2", "vision_model.transformer.layers.12.self_attn.q_proj", "vision_model.transformer.layers.12.self_attn.k_proj", "vision_model.transformer.layers.12.self_attn.v_proj", "vision_model.transformer.layers.12.self_attn.o_proj", "vision_model.transformer.layers.12.mlp.fc1", "vision_model.transformer.layers.12.mlp.fc2", "vision_model.transformer.layers.13.self_attn.q_proj", "vision_model.transformer.layers.13.self_attn.k_proj", "vision_model.transformer.layers.13.self_attn.v_proj", "vision_model.transformer.layers.13.self_attn.o_proj", "vision_model.transformer.layers.13.mlp.fc1", "vision_model.transformer.layers.13.mlp.fc2", "vision_model.transformer.layers.14.self_attn.q_proj", "vision_model.transformer.layers.14.self_attn.k_proj", "vision_model.transformer.layers.14.self_attn.v_proj", "vision_model.transformer.layers.14.self_attn.o_proj", "vision_model.transformer.layers.14.mlp.fc1", "vision_model.transformer.layers.14.mlp.fc2", "vision_model.transformer.layers.15.self_attn.q_proj", "vision_model.transformer.layers.15.self_attn.k_proj", "vision_model.transformer.layers.15.self_attn.v_proj", "vision_model.transformer.layers.15.self_attn.o_proj", "vision_model.transformer.layers.15.mlp.fc1", "vision_model.transformer.layers.15.mlp.fc2", "vision_model.transformer.layers.16.self_attn.q_proj", "vision_model.transformer.layers.16.self_attn.k_proj", "vision_model.transformer.layers.16.self_attn.v_proj", "vision_model.transformer.layers.16.self_attn.o_proj", "vision_model.transformer.layers.16.mlp.fc1", "vision_model.transformer.layers.16.mlp.fc2", "vision_model.transformer.layers.17.self_attn.q_proj", "vision_model.transformer.layers.17.self_attn.k_proj", "vision_model.transformer.layers.17.self_attn.v_proj", "vision_model.transformer.layers.17.self_attn.o_proj", "vision_model.transformer.layers.17.mlp.fc1", "vision_model.transformer.layers.17.mlp.fc2", "vision_model.transformer.layers.18.self_attn.q_proj", "vision_model.transformer.layers.18.self_attn.k_proj", "vision_model.transformer.layers.18.self_attn.v_proj", "vision_model.transformer.layers.18.self_attn.o_proj", "vision_model.transformer.layers.18.mlp.fc1", "vision_model.transformer.layers.18.mlp.fc2", "vision_model.transformer.layers.19.self_attn.q_proj", "vision_model.transformer.layers.19.self_attn.k_proj", "vision_model.transformer.layers.19.self_attn.v_proj", "vision_model.transformer.layers.19.self_attn.o_proj", "vision_model.transformer.layers.19.mlp.fc1", "vision_model.transformer.layers.19.mlp.fc2", "vision_model.transformer.layers.20.self_attn.q_proj", "vision_model.transformer.layers.20.self_attn.k_proj", "vision_model.transformer.layers.20.self_attn.v_proj", "vision_model.transformer.layers.20.self_attn.o_proj", "vision_model.transformer.layers.20.mlp.fc1", "vision_model.transformer.layers.20.mlp.fc2", "vision_model.transformer.layers.21.self_attn.q_proj", "vision_model.transformer.layers.21.self_attn.k_proj", "vision_model.transformer.layers.21.self_attn.v_proj", "vision_model.transformer.layers.21.self_attn.o_proj", "vision_model.transformer.layers.21.mlp.fc1", "vision_model.transformer.layers.21.mlp.fc2", "vision_model.transformer.layers.22.self_attn.q_proj", "vision_model.transformer.layers.22.self_attn.k_proj", "vision_model.transformer.layers.22.self_attn.v_proj", "vision_model.transformer.layers.22.self_attn.o_proj", "vision_model.transformer.layers.22.mlp.fc1", "vision_model.transformer.layers.22.mlp.fc2", "vision_model.transformer.layers.23.self_attn.q_proj", "vision_model.transformer.layers.23.self_attn.k_proj", "vision_model.transformer.layers.23.self_attn.v_proj", "vision_model.transformer.layers.23.self_attn.o_proj", "vision_model.transformer.layers.23.mlp.fc1", "vision_model.transformer.layers.23.mlp.fc2", "vision_model.transformer.layers.24.self_attn.q_proj", "vision_model.transformer.layers.24.self_attn.k_proj", "vision_model.transformer.layers.24.self_attn.v_proj", "vision_model.transformer.layers.24.self_attn.o_proj", "vision_model.transformer.layers.24.mlp.fc1", "vision_model.transformer.layers.24.mlp.fc2", "vision_model.transformer.layers.25.self_attn.q_proj", "vision_model.transformer.layers.25.self_attn.k_proj", "vision_model.transformer.layers.25.self_attn.v_proj", "vision_model.transformer.layers.25.self_attn.o_proj", "vision_model.transformer.layers.25.mlp.fc1", "vision_model.transformer.layers.25.mlp.fc2", "vision_model.transformer.layers.26.self_attn.q_proj", "vision_model.transformer.layers.26.self_attn.k_proj", "vision_model.transformer.layers.26.self_attn.v_proj", "vision_model.transformer.layers.26.self_attn.o_proj", "vision_model.transformer.layers.26.mlp.fc1", "vision_model.transformer.layers.26.mlp.fc2", "vision_model.transformer.layers.27.self_attn.q_proj", "vision_model.transformer.layers.27.self_attn.k_proj", "vision_model.transformer.layers.27.self_attn.v_proj", "vision_model.transformer.layers.27.self_attn.o_proj", "vision_model.transformer.layers.27.mlp.fc1", "vision_model.transformer.layers.27.mlp.fc2", "vision_model.transformer.layers.28.self_attn.q_proj", "vision_model.transformer.layers.28.self_attn.k_proj", "vision_model.transformer.layers.28.self_attn.v_proj", "vision_model.transformer.layers.28.self_attn.o_proj", "vision_model.transformer.layers.28.mlp.fc1", "vision_model.transformer.layers.28.mlp.fc2", "vision_model.transformer.layers.29.self_attn.q_proj", "vision_model.transformer.layers.29.self_attn.k_proj", "vision_model.transformer.layers.29.self_attn.v_proj", "vision_model.transformer.layers.29.self_attn.o_proj", "vision_model.transformer.layers.29.mlp.fc1", "vision_model.transformer.layers.29.mlp.fc2", "vision_model.transformer.layers.30.self_attn.q_proj", "vision_model.transformer.layers.30.self_attn.k_proj", "vision_model.transformer.layers.30.self_attn.v_proj", "vision_model.transformer.layers.30.self_attn.o_proj", "vision_model.transformer.layers.30.mlp.fc1", "vision_model.transformer.layers.30.mlp.fc2", "vision_model.transformer.layers.31.self_attn.q_proj", "vision_model.transformer.layers.31.self_attn.k_proj", "vision_model.transformer.layers.31.self_attn.v_proj", "vision_model.transformer.layers.31.self_attn.o_proj", "vision_model.transformer.layers.31.mlp.fc1", "vision_model.transformer.layers.31.mlp.fc2", "vision_model.global_transformer.layers.0.self_attn.q_proj", "vision_model.global_transformer.layers.0.self_attn.k_proj", "vision_model.global_transformer.layers.0.self_attn.v_proj", "vision_model.global_transformer.layers.0.self_attn.o_proj", "vision_model.global_transformer.layers.0.mlp.fc1", "vision_model.global_transformer.layers.0.mlp.fc2", "vision_model.global_transformer.layers.1.self_attn.q_proj", "vision_model.global_transformer.layers.1.self_attn.k_proj", "vision_model.global_transformer.layers.1.self_attn.v_proj", "vision_model.global_transformer.layers.1.self_attn.o_proj", "vision_model.global_transformer.layers.1.mlp.fc1", "vision_model.global_transformer.layers.1.mlp.fc2", "vision_model.global_transformer.layers.2.self_attn.q_proj", "vision_model.global_transformer.layers.2.self_attn.k_proj", "vision_model.global_transformer.layers.2.self_attn.v_proj", "vision_model.global_transformer.layers.2.self_attn.o_proj", "vision_model.global_transformer.layers.2.mlp.fc1", "vision_model.global_transformer.layers.2.mlp.fc2", "vision_model.global_transformer.layers.3.self_attn.q_proj", "vision_model.global_transformer.layers.3.self_attn.k_proj", "vision_model.global_transformer.layers.3.self_attn.v_proj", "vision_model.global_transformer.layers.3.self_attn.o_proj", "vision_model.global_transformer.layers.3.mlp.fc1", "vision_model.global_transformer.layers.3.mlp.fc2", "vision_model.global_transformer.layers.4.self_attn.q_proj", "vision_model.global_transformer.layers.4.self_attn.k_proj", "vision_model.global_transformer.layers.4.self_attn.v_proj", "vision_model.global_transformer.layers.4.self_attn.o_proj", "vision_model.global_transformer.layers.4.mlp.fc1", "vision_model.global_transformer.layers.4.mlp.fc2", "vision_model.global_transformer.layers.5.self_attn.q_proj", "vision_model.global_transformer.layers.5.self_attn.k_proj", "vision_model.global_transformer.layers.5.self_attn.v_proj", "vision_model.global_transformer.layers.5.self_attn.o_proj", "vision_model.global_transformer.layers.5.mlp.fc1", "vision_model.global_transformer.layers.5.mlp.fc2", "vision_model.global_transformer.layers.6.self_attn.q_proj", "vision_model.global_transformer.layers.6.self_attn.k_proj", "vision_model.global_transformer.layers.6.self_attn.v_proj", "vision_model.global_transformer.layers.6.self_attn.o_proj", "vision_model.global_transformer.layers.6.mlp.fc1", "vision_model.global_transformer.layers.6.mlp.fc2", "vision_model.global_transformer.layers.7.self_attn.q_proj", "vision_model.global_transformer.layers.7.self_attn.k_proj", "vision_model.global_transformer.layers.7.self_attn.v_proj", "vision_model.global_transformer.layers.7.self_attn.o_proj", "vision_model.global_transformer.layers.7.mlp.fc1", "vision_model.global_transformer.layers.7.mlp.fc2", "language_model.lm_head", "multi_modal_projector" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": { "format": "dense", "global_sparsity": 0.125959880790898, "ignore": [ "vision_model.transformer.layers.0.self_attn.q_proj", "vision_model.transformer.layers.0.self_attn.k_proj", "vision_model.transformer.layers.0.self_attn.v_proj", "vision_model.transformer.layers.0.self_attn.o_proj", "vision_model.transformer.layers.0.mlp.fc1", "vision_model.transformer.layers.0.mlp.fc2", "vision_model.transformer.layers.1.self_attn.q_proj", "vision_model.transformer.layers.1.self_attn.k_proj", "vision_model.transformer.layers.1.self_attn.v_proj", "vision_model.transformer.layers.1.self_attn.o_proj", "vision_model.transformer.layers.1.mlp.fc1", "vision_model.transformer.layers.1.mlp.fc2", "vision_model.transformer.layers.2.self_attn.q_proj", "vision_model.transformer.layers.2.self_attn.k_proj", "vision_model.transformer.layers.2.self_attn.v_proj", "vision_model.transformer.layers.2.self_attn.o_proj", "vision_model.transformer.layers.2.mlp.fc1", "vision_model.transformer.layers.2.mlp.fc2", "vision_model.transformer.layers.3.self_attn.q_proj", "vision_model.transformer.layers.3.self_attn.k_proj", "vision_model.transformer.layers.3.self_attn.v_proj", "vision_model.transformer.layers.3.self_attn.o_proj", "vision_model.transformer.layers.3.mlp.fc1", "vision_model.transformer.layers.3.mlp.fc2", "vision_model.transformer.layers.4.self_attn.q_proj", "vision_model.transformer.layers.4.self_attn.k_proj", "vision_model.transformer.layers.4.self_attn.v_proj", "vision_model.transformer.layers.4.self_attn.o_proj", "vision_model.transformer.layers.4.mlp.fc1", "vision_model.transformer.layers.4.mlp.fc2", "vision_model.transformer.layers.5.self_attn.q_proj", "vision_model.transformer.layers.5.self_attn.k_proj", "vision_model.transformer.layers.5.self_attn.v_proj", "vision_model.transformer.layers.5.self_attn.o_proj", "vision_model.transformer.layers.5.mlp.fc1", "vision_model.transformer.layers.5.mlp.fc2", "vision_model.transformer.layers.6.self_attn.q_proj", "vision_model.transformer.layers.6.self_attn.k_proj", "vision_model.transformer.layers.6.self_attn.v_proj", "vision_model.transformer.layers.6.self_attn.o_proj", "vision_model.transformer.layers.6.mlp.fc1", "vision_model.transformer.layers.6.mlp.fc2", "vision_model.transformer.layers.7.self_attn.q_proj", "vision_model.transformer.layers.7.self_attn.k_proj", "vision_model.transformer.layers.7.self_attn.v_proj", "vision_model.transformer.layers.7.self_attn.o_proj", "vision_model.transformer.layers.7.mlp.fc1", "vision_model.transformer.layers.7.mlp.fc2", "vision_model.transformer.layers.8.self_attn.q_proj", "vision_model.transformer.layers.8.self_attn.k_proj", "vision_model.transformer.layers.8.self_attn.v_proj", "vision_model.transformer.layers.8.self_attn.o_proj", "vision_model.transformer.layers.8.mlp.fc1", "vision_model.transformer.layers.8.mlp.fc2", "vision_model.transformer.layers.9.self_attn.q_proj", "vision_model.transformer.layers.9.self_attn.k_proj", "vision_model.transformer.layers.9.self_attn.v_proj", "vision_model.transformer.layers.9.self_attn.o_proj", "vision_model.transformer.layers.9.mlp.fc1", "vision_model.transformer.layers.9.mlp.fc2", "vision_model.transformer.layers.10.self_attn.q_proj", "vision_model.transformer.layers.10.self_attn.k_proj", "vision_model.transformer.layers.10.self_attn.v_proj", "vision_model.transformer.layers.10.self_attn.o_proj", "vision_model.transformer.layers.10.mlp.fc1", "vision_model.transformer.layers.10.mlp.fc2", "vision_model.transformer.layers.11.self_attn.q_proj", "vision_model.transformer.layers.11.self_attn.k_proj", "vision_model.transformer.layers.11.self_attn.v_proj", "vision_model.transformer.layers.11.self_attn.o_proj", "vision_model.transformer.layers.11.mlp.fc1", "vision_model.transformer.layers.11.mlp.fc2", "vision_model.transformer.layers.12.self_attn.q_proj", "vision_model.transformer.layers.12.self_attn.k_proj", "vision_model.transformer.layers.12.self_attn.v_proj", "vision_model.transformer.layers.12.self_attn.o_proj", "vision_model.transformer.layers.12.mlp.fc1", "vision_model.transformer.layers.12.mlp.fc2", "vision_model.transformer.layers.13.self_attn.q_proj", "vision_model.transformer.layers.13.self_attn.k_proj", "vision_model.transformer.layers.13.self_attn.v_proj", "vision_model.transformer.layers.13.self_attn.o_proj", "vision_model.transformer.layers.13.mlp.fc1", "vision_model.transformer.layers.13.mlp.fc2", "vision_model.transformer.layers.14.self_attn.q_proj", "vision_model.transformer.layers.14.self_attn.k_proj", "vision_model.transformer.layers.14.self_attn.v_proj", "vision_model.transformer.layers.14.self_attn.o_proj", "vision_model.transformer.layers.14.mlp.fc1", "vision_model.transformer.layers.14.mlp.fc2", "vision_model.transformer.layers.15.self_attn.q_proj", "vision_model.transformer.layers.15.self_attn.k_proj", "vision_model.transformer.layers.15.self_attn.v_proj", "vision_model.transformer.layers.15.self_attn.o_proj", "vision_model.transformer.layers.15.mlp.fc1", "vision_model.transformer.layers.15.mlp.fc2", "vision_model.transformer.layers.16.self_attn.q_proj", "vision_model.transformer.layers.16.self_attn.k_proj", "vision_model.transformer.layers.16.self_attn.v_proj", "vision_model.transformer.layers.16.self_attn.o_proj", "vision_model.transformer.layers.16.mlp.fc1", "vision_model.transformer.layers.16.mlp.fc2", "vision_model.transformer.layers.17.self_attn.q_proj", "vision_model.transformer.layers.17.self_attn.k_proj", "vision_model.transformer.layers.17.self_attn.v_proj", "vision_model.transformer.layers.17.self_attn.o_proj", "vision_model.transformer.layers.17.mlp.fc1", "vision_model.transformer.layers.17.mlp.fc2", "vision_model.transformer.layers.18.self_attn.q_proj", "vision_model.transformer.layers.18.self_attn.k_proj", "vision_model.transformer.layers.18.self_attn.v_proj", "vision_model.transformer.layers.18.self_attn.o_proj", "vision_model.transformer.layers.18.mlp.fc1", "vision_model.transformer.layers.18.mlp.fc2", "vision_model.transformer.layers.19.self_attn.q_proj", "vision_model.transformer.layers.19.self_attn.k_proj", "vision_model.transformer.layers.19.self_attn.v_proj", "vision_model.transformer.layers.19.self_attn.o_proj", "vision_model.transformer.layers.19.mlp.fc1", "vision_model.transformer.layers.19.mlp.fc2", "vision_model.transformer.layers.20.self_attn.q_proj", "vision_model.transformer.layers.20.self_attn.k_proj", "vision_model.transformer.layers.20.self_attn.v_proj", "vision_model.transformer.layers.20.self_attn.o_proj", "vision_model.transformer.layers.20.mlp.fc1", "vision_model.transformer.layers.20.mlp.fc2", "vision_model.transformer.layers.21.self_attn.q_proj", "vision_model.transformer.layers.21.self_attn.k_proj", "vision_model.transformer.layers.21.self_attn.v_proj", "vision_model.transformer.layers.21.self_attn.o_proj", "vision_model.transformer.layers.21.mlp.fc1", "vision_model.transformer.layers.21.mlp.fc2", "vision_model.transformer.layers.22.self_attn.q_proj", "vision_model.transformer.layers.22.self_attn.k_proj", "vision_model.transformer.layers.22.self_attn.v_proj", "vision_model.transformer.layers.22.self_attn.o_proj", "vision_model.transformer.layers.22.mlp.fc1", "vision_model.transformer.layers.22.mlp.fc2", "vision_model.transformer.layers.23.self_attn.q_proj", "vision_model.transformer.layers.23.self_attn.k_proj", "vision_model.transformer.layers.23.self_attn.v_proj", "vision_model.transformer.layers.23.self_attn.o_proj", "vision_model.transformer.layers.23.mlp.fc1", "vision_model.transformer.layers.23.mlp.fc2", "vision_model.transformer.layers.24.self_attn.q_proj", "vision_model.transformer.layers.24.self_attn.k_proj", "vision_model.transformer.layers.24.self_attn.v_proj", "vision_model.transformer.layers.24.self_attn.o_proj", "vision_model.transformer.layers.24.mlp.fc1", "vision_model.transformer.layers.24.mlp.fc2", "vision_model.transformer.layers.25.self_attn.q_proj", "vision_model.transformer.layers.25.self_attn.k_proj", "vision_model.transformer.layers.25.self_attn.v_proj", "vision_model.transformer.layers.25.self_attn.o_proj", "vision_model.transformer.layers.25.mlp.fc1", "vision_model.transformer.layers.25.mlp.fc2", "vision_model.transformer.layers.26.self_attn.q_proj", "vision_model.transformer.layers.26.self_attn.k_proj", "vision_model.transformer.layers.26.self_attn.v_proj", "vision_model.transformer.layers.26.self_attn.o_proj", "vision_model.transformer.layers.26.mlp.fc1", "vision_model.transformer.layers.26.mlp.fc2", "vision_model.transformer.layers.27.self_attn.q_proj", "vision_model.transformer.layers.27.self_attn.k_proj", "vision_model.transformer.layers.27.self_attn.v_proj", "vision_model.transformer.layers.27.self_attn.o_proj", "vision_model.transformer.layers.27.mlp.fc1", "vision_model.transformer.layers.27.mlp.fc2", "vision_model.transformer.layers.28.self_attn.q_proj", "vision_model.transformer.layers.28.self_attn.k_proj", "vision_model.transformer.layers.28.self_attn.v_proj", "vision_model.transformer.layers.28.self_attn.o_proj", "vision_model.transformer.layers.28.mlp.fc1", "vision_model.transformer.layers.28.mlp.fc2", "vision_model.transformer.layers.29.self_attn.q_proj", "vision_model.transformer.layers.29.self_attn.k_proj", "vision_model.transformer.layers.29.self_attn.v_proj", "vision_model.transformer.layers.29.self_attn.o_proj", "vision_model.transformer.layers.29.mlp.fc1", "vision_model.transformer.layers.29.mlp.fc2", "vision_model.transformer.layers.30.self_attn.q_proj", "vision_model.transformer.layers.30.self_attn.k_proj", "vision_model.transformer.layers.30.self_attn.v_proj", "vision_model.transformer.layers.30.self_attn.o_proj", "vision_model.transformer.layers.30.mlp.fc1", "vision_model.transformer.layers.30.mlp.fc2", "vision_model.transformer.layers.31.self_attn.q_proj", "vision_model.transformer.layers.31.self_attn.k_proj", "vision_model.transformer.layers.31.self_attn.v_proj", "vision_model.transformer.layers.31.self_attn.o_proj", "vision_model.transformer.layers.31.mlp.fc1", "vision_model.transformer.layers.31.mlp.fc2", "vision_model.global_transformer.layers.0.self_attn.q_proj", "vision_model.global_transformer.layers.0.self_attn.k_proj", "vision_model.global_transformer.layers.0.self_attn.v_proj", "vision_model.global_transformer.layers.0.self_attn.o_proj", "vision_model.global_transformer.layers.0.mlp.fc1", "vision_model.global_transformer.layers.0.mlp.fc2", "vision_model.global_transformer.layers.1.self_attn.q_proj", "vision_model.global_transformer.layers.1.self_attn.k_proj", "vision_model.global_transformer.layers.1.self_attn.v_proj", "vision_model.global_transformer.layers.1.self_attn.o_proj", "vision_model.global_transformer.layers.1.mlp.fc1", "vision_model.global_transformer.layers.1.mlp.fc2", "vision_model.global_transformer.layers.2.self_attn.q_proj", "vision_model.global_transformer.layers.2.self_attn.k_proj", "vision_model.global_transformer.layers.2.self_attn.v_proj", "vision_model.global_transformer.layers.2.self_attn.o_proj", "vision_model.global_transformer.layers.2.mlp.fc1", "vision_model.global_transformer.layers.2.mlp.fc2", "vision_model.global_transformer.layers.3.self_attn.q_proj", "vision_model.global_transformer.layers.3.self_attn.k_proj", "vision_model.global_transformer.layers.3.self_attn.v_proj", "vision_model.global_transformer.layers.3.self_attn.o_proj", "vision_model.global_transformer.layers.3.mlp.fc1", "vision_model.global_transformer.layers.3.mlp.fc2", "vision_model.global_transformer.layers.4.self_attn.q_proj", "vision_model.global_transformer.layers.4.self_attn.k_proj", "vision_model.global_transformer.layers.4.self_attn.v_proj", "vision_model.global_transformer.layers.4.self_attn.o_proj", "vision_model.global_transformer.layers.4.mlp.fc1", "vision_model.global_transformer.layers.4.mlp.fc2", "vision_model.global_transformer.layers.5.self_attn.q_proj", "vision_model.global_transformer.layers.5.self_attn.k_proj", "vision_model.global_transformer.layers.5.self_attn.v_proj", "vision_model.global_transformer.layers.5.self_attn.o_proj", "vision_model.global_transformer.layers.5.mlp.fc1", "vision_model.global_transformer.layers.5.mlp.fc2", "vision_model.global_transformer.layers.6.self_attn.q_proj", "vision_model.global_transformer.layers.6.self_attn.k_proj", "vision_model.global_transformer.layers.6.self_attn.v_proj", "vision_model.global_transformer.layers.6.self_attn.o_proj", "vision_model.global_transformer.layers.6.mlp.fc1", "vision_model.global_transformer.layers.6.mlp.fc2", "vision_model.global_transformer.layers.7.self_attn.q_proj", "vision_model.global_transformer.layers.7.self_attn.k_proj", "vision_model.global_transformer.layers.7.self_attn.v_proj", "vision_model.global_transformer.layers.7.self_attn.o_proj", "vision_model.global_transformer.layers.7.mlp.fc1", "vision_model.global_transformer.layers.7.mlp.fc2", "language_model.model.layers.0.self_attn.o_proj", "language_model.model.layers.0.mlp.gate_proj", "language_model.model.layers.0.mlp.up_proj", "language_model.model.layers.0.mlp.down_proj", "language_model.model.layers.1.self_attn.v_proj", "language_model.model.layers.1.self_attn.o_proj", "language_model.model.layers.1.mlp.gate_proj", "language_model.model.layers.1.mlp.up_proj", "language_model.model.layers.1.mlp.down_proj", "language_model.model.layers.2.self_attn.q_proj", "language_model.model.layers.2.self_attn.k_proj", "language_model.model.layers.2.self_attn.v_proj", "language_model.model.layers.2.self_attn.o_proj", "language_model.model.layers.2.mlp.gate_proj", "language_model.model.layers.2.mlp.up_proj", "language_model.model.layers.2.mlp.down_proj", "language_model.model.layers.3.cross_attn.q_proj", "language_model.model.layers.3.cross_attn.k_proj", "language_model.model.layers.3.cross_attn.v_proj", "language_model.model.layers.3.cross_attn.o_proj", "language_model.model.layers.3.mlp.gate_proj", "language_model.model.layers.3.mlp.up_proj", "language_model.model.layers.3.mlp.down_proj", "language_model.model.layers.4.self_attn.q_proj", "language_model.model.layers.4.self_attn.k_proj", "language_model.model.layers.4.self_attn.v_proj", "language_model.model.layers.4.self_attn.o_proj", "language_model.model.layers.4.mlp.gate_proj", "language_model.model.layers.4.mlp.up_proj", "language_model.model.layers.4.mlp.down_proj", "language_model.model.layers.5.self_attn.q_proj", "language_model.model.layers.5.self_attn.k_proj", "language_model.model.layers.5.self_attn.v_proj", "language_model.model.layers.5.self_attn.o_proj", "language_model.model.layers.5.mlp.gate_proj", "language_model.model.layers.5.mlp.up_proj", "language_model.model.layers.5.mlp.down_proj", "language_model.model.layers.6.self_attn.q_proj", "language_model.model.layers.6.self_attn.k_proj", "language_model.model.layers.6.self_attn.v_proj", "language_model.model.layers.6.self_attn.o_proj", "language_model.model.layers.6.mlp.gate_proj", "language_model.model.layers.6.mlp.up_proj", "language_model.model.layers.6.mlp.down_proj", "language_model.model.layers.7.self_attn.q_proj", "language_model.model.layers.7.self_attn.k_proj", "language_model.model.layers.7.self_attn.v_proj", "language_model.model.layers.7.self_attn.o_proj", "language_model.model.layers.7.mlp.gate_proj", "language_model.model.layers.7.mlp.up_proj", "language_model.model.layers.7.mlp.down_proj", "language_model.model.layers.8.cross_attn.q_proj", "language_model.model.layers.8.cross_attn.k_proj", "language_model.model.layers.8.cross_attn.v_proj", "language_model.model.layers.8.cross_attn.o_proj", "language_model.model.layers.8.mlp.gate_proj", "language_model.model.layers.8.mlp.up_proj", "language_model.model.layers.8.mlp.down_proj", "language_model.model.layers.9.self_attn.q_proj", "language_model.model.layers.9.self_attn.k_proj", "language_model.model.layers.9.self_attn.v_proj", "language_model.model.layers.9.self_attn.o_proj", "language_model.model.layers.9.mlp.gate_proj", "language_model.model.layers.9.mlp.up_proj", "language_model.model.layers.9.mlp.down_proj", "language_model.model.layers.10.self_attn.q_proj", "language_model.model.layers.10.self_attn.k_proj", "language_model.model.layers.10.self_attn.v_proj", "language_model.model.layers.10.self_attn.o_proj", "language_model.model.layers.10.mlp.gate_proj", "language_model.model.layers.10.mlp.up_proj", "language_model.model.layers.10.mlp.down_proj", "language_model.model.layers.11.self_attn.q_proj", "language_model.model.layers.11.self_attn.k_proj", "language_model.model.layers.11.self_attn.v_proj", "language_model.model.layers.11.self_attn.o_proj", "language_model.model.layers.11.mlp.gate_proj", "language_model.model.layers.11.mlp.up_proj", "language_model.model.layers.11.mlp.down_proj", "language_model.model.layers.12.self_attn.q_proj", "language_model.model.layers.12.self_attn.k_proj", "language_model.model.layers.12.self_attn.v_proj", "language_model.model.layers.12.self_attn.o_proj", "language_model.model.layers.12.mlp.gate_proj", "language_model.model.layers.12.mlp.up_proj", "language_model.model.layers.12.mlp.down_proj", "language_model.model.layers.13.cross_attn.q_proj", "language_model.model.layers.13.cross_attn.k_proj", "language_model.model.layers.13.cross_attn.v_proj", "language_model.model.layers.13.cross_attn.o_proj", "language_model.model.layers.13.mlp.gate_proj", "language_model.model.layers.13.mlp.up_proj", "language_model.model.layers.13.mlp.down_proj", "language_model.model.layers.14.self_attn.q_proj", "language_model.model.layers.14.self_attn.k_proj", "language_model.model.layers.14.self_attn.v_proj", "language_model.model.layers.14.self_attn.o_proj", "language_model.model.layers.14.mlp.gate_proj", "language_model.model.layers.14.mlp.up_proj", "language_model.model.layers.14.mlp.down_proj", "language_model.model.layers.15.self_attn.q_proj", "language_model.model.layers.15.self_attn.k_proj", "language_model.model.layers.15.self_attn.v_proj", "language_model.model.layers.15.self_attn.o_proj", "language_model.model.layers.15.mlp.gate_proj", "language_model.model.layers.15.mlp.up_proj", "language_model.model.layers.15.mlp.down_proj", "language_model.model.layers.16.self_attn.q_proj", "language_model.model.layers.16.self_attn.k_proj", "language_model.model.layers.16.self_attn.v_proj", "language_model.model.layers.16.self_attn.o_proj", "language_model.model.layers.16.mlp.gate_proj", "language_model.model.layers.16.mlp.up_proj", "language_model.model.layers.16.mlp.down_proj", "language_model.model.layers.17.self_attn.q_proj", "language_model.model.layers.17.self_attn.k_proj", "language_model.model.layers.17.self_attn.v_proj", "language_model.model.layers.17.self_attn.o_proj", "language_model.model.layers.17.mlp.gate_proj", "language_model.model.layers.17.mlp.up_proj", "language_model.model.layers.17.mlp.down_proj", "language_model.model.layers.18.cross_attn.q_proj", "language_model.model.layers.18.cross_attn.k_proj", "language_model.model.layers.18.cross_attn.v_proj", "language_model.model.layers.18.cross_attn.o_proj", "language_model.model.layers.18.mlp.gate_proj", "language_model.model.layers.18.mlp.up_proj", "language_model.model.layers.18.mlp.down_proj", "language_model.model.layers.19.self_attn.q_proj", "language_model.model.layers.19.self_attn.k_proj", "language_model.model.layers.19.self_attn.v_proj", "language_model.model.layers.19.self_attn.o_proj", "language_model.model.layers.19.mlp.gate_proj", "language_model.model.layers.19.mlp.up_proj", "language_model.model.layers.19.mlp.down_proj", "language_model.model.layers.20.self_attn.q_proj", "language_model.model.layers.20.self_attn.k_proj", "language_model.model.layers.20.self_attn.v_proj", "language_model.model.layers.20.self_attn.o_proj", "language_model.model.layers.20.mlp.gate_proj", "language_model.model.layers.20.mlp.up_proj", "language_model.model.layers.20.mlp.down_proj", "language_model.model.layers.21.self_attn.q_proj", "language_model.model.layers.21.self_attn.k_proj", "language_model.model.layers.21.self_attn.v_proj", "language_model.model.layers.21.self_attn.o_proj", "language_model.model.layers.21.mlp.gate_proj", "language_model.model.layers.21.mlp.up_proj", "language_model.model.layers.21.mlp.down_proj", "language_model.model.layers.22.self_attn.q_proj", "language_model.model.layers.22.self_attn.k_proj", "language_model.model.layers.22.self_attn.v_proj", "language_model.model.layers.22.self_attn.o_proj", "language_model.model.layers.22.mlp.gate_proj", "language_model.model.layers.22.mlp.up_proj", "language_model.model.layers.22.mlp.down_proj", "language_model.model.layers.23.cross_attn.q_proj", "language_model.model.layers.23.cross_attn.k_proj", "language_model.model.layers.23.cross_attn.v_proj", "language_model.model.layers.23.cross_attn.o_proj", "language_model.model.layers.23.mlp.gate_proj", "language_model.model.layers.23.mlp.up_proj", "language_model.model.layers.23.mlp.down_proj", "language_model.model.layers.24.self_attn.q_proj", "language_model.model.layers.24.self_attn.k_proj", "language_model.model.layers.24.self_attn.v_proj", "language_model.model.layers.24.self_attn.o_proj", "language_model.model.layers.24.mlp.gate_proj", "language_model.model.layers.24.mlp.up_proj", "language_model.model.layers.24.mlp.down_proj", "language_model.model.layers.25.self_attn.q_proj", "language_model.model.layers.25.self_attn.k_proj", "language_model.model.layers.25.self_attn.v_proj", "language_model.model.layers.25.self_attn.o_proj", "language_model.model.layers.25.mlp.gate_proj", "language_model.model.layers.25.mlp.up_proj", "language_model.model.layers.25.mlp.down_proj", "language_model.model.layers.26.self_attn.q_proj", "language_model.model.layers.26.self_attn.k_proj", "language_model.model.layers.26.self_attn.v_proj", "language_model.model.layers.26.self_attn.o_proj", "language_model.model.layers.26.mlp.gate_proj", "language_model.model.layers.26.mlp.up_proj", "language_model.model.layers.26.mlp.down_proj", "language_model.model.layers.27.self_attn.q_proj", "language_model.model.layers.27.self_attn.k_proj", "language_model.model.layers.27.self_attn.v_proj", "language_model.model.layers.27.self_attn.o_proj", "language_model.model.layers.27.mlp.gate_proj", "language_model.model.layers.27.mlp.up_proj", "language_model.model.layers.27.mlp.down_proj", "language_model.model.layers.28.cross_attn.q_proj", "language_model.model.layers.28.cross_attn.k_proj", "language_model.model.layers.28.cross_attn.v_proj", "language_model.model.layers.28.cross_attn.o_proj", "language_model.model.layers.28.mlp.gate_proj", "language_model.model.layers.28.mlp.up_proj", "language_model.model.layers.28.mlp.down_proj", "language_model.model.layers.29.self_attn.q_proj", "language_model.model.layers.29.self_attn.k_proj", "language_model.model.layers.29.self_attn.v_proj", "language_model.model.layers.29.self_attn.o_proj", "language_model.model.layers.29.mlp.gate_proj", "language_model.model.layers.29.mlp.up_proj", "language_model.model.layers.29.mlp.down_proj", "language_model.model.layers.30.self_attn.q_proj", "language_model.model.layers.30.self_attn.k_proj", "language_model.model.layers.30.self_attn.v_proj", "language_model.model.layers.30.self_attn.o_proj", "language_model.model.layers.30.mlp.gate_proj", "language_model.model.layers.30.mlp.up_proj", "language_model.model.layers.30.mlp.down_proj", "language_model.model.layers.31.self_attn.q_proj", "language_model.model.layers.31.self_attn.k_proj", "language_model.model.layers.31.self_attn.v_proj", "language_model.model.layers.31.self_attn.o_proj", "language_model.model.layers.31.mlp.gate_proj", "language_model.model.layers.31.mlp.up_proj", "language_model.model.layers.31.mlp.down_proj", "language_model.model.layers.32.self_attn.q_proj", "language_model.model.layers.32.self_attn.k_proj", "language_model.model.layers.32.self_attn.v_proj", "language_model.model.layers.32.self_attn.o_proj", "language_model.model.layers.32.mlp.gate_proj", "language_model.model.layers.32.mlp.up_proj", "language_model.model.layers.32.mlp.down_proj", "language_model.model.layers.33.cross_attn.q_proj", "language_model.model.layers.33.cross_attn.k_proj", "language_model.model.layers.33.cross_attn.v_proj", "language_model.model.layers.33.cross_attn.o_proj", "language_model.model.layers.33.mlp.gate_proj", "language_model.model.layers.33.mlp.up_proj", "language_model.model.layers.33.mlp.down_proj", "language_model.model.layers.34.self_attn.q_proj", "language_model.model.layers.34.self_attn.k_proj", "language_model.model.layers.34.self_attn.v_proj", "language_model.model.layers.34.self_attn.o_proj", "language_model.model.layers.34.mlp.gate_proj", "language_model.model.layers.34.mlp.up_proj", "language_model.model.layers.34.mlp.down_proj", "language_model.model.layers.35.self_attn.q_proj", "language_model.model.layers.35.self_attn.k_proj", "language_model.model.layers.35.self_attn.v_proj", "language_model.model.layers.35.self_attn.o_proj", "language_model.model.layers.35.mlp.gate_proj", "language_model.model.layers.35.mlp.up_proj", "language_model.model.layers.35.mlp.down_proj", "language_model.model.layers.36.self_attn.q_proj", "language_model.model.layers.36.self_attn.k_proj", "language_model.model.layers.36.self_attn.v_proj", "language_model.model.layers.36.self_attn.o_proj", "language_model.model.layers.36.mlp.gate_proj", "language_model.model.layers.36.mlp.up_proj", "language_model.model.layers.36.mlp.down_proj", "language_model.model.layers.37.self_attn.q_proj", "language_model.model.layers.37.self_attn.k_proj", "language_model.model.layers.37.self_attn.v_proj", "language_model.model.layers.37.self_attn.o_proj", "language_model.model.layers.37.mlp.gate_proj", "language_model.model.layers.37.mlp.up_proj", "language_model.model.layers.37.mlp.down_proj", "language_model.model.layers.38.cross_attn.q_proj", "language_model.model.layers.38.cross_attn.k_proj", "language_model.model.layers.38.cross_attn.v_proj", "language_model.model.layers.38.cross_attn.o_proj", "language_model.model.layers.38.mlp.gate_proj", "language_model.model.layers.38.mlp.up_proj", "language_model.model.layers.38.mlp.down_proj", "language_model.model.layers.39.self_attn.q_proj", "language_model.model.layers.39.self_attn.k_proj", "language_model.model.layers.39.self_attn.v_proj", "language_model.model.layers.39.self_attn.o_proj", "language_model.model.layers.39.mlp.gate_proj", "language_model.model.layers.39.mlp.up_proj", "language_model.model.layers.39.mlp.down_proj", "language_model.model.layers.40.self_attn.q_proj", "language_model.model.layers.40.self_attn.k_proj", "language_model.model.layers.40.self_attn.v_proj", "language_model.model.layers.40.self_attn.o_proj", "language_model.model.layers.40.mlp.gate_proj", "language_model.model.layers.40.mlp.up_proj", "language_model.model.layers.40.mlp.down_proj", "language_model.model.layers.41.self_attn.q_proj", "language_model.model.layers.41.self_attn.k_proj", "language_model.model.layers.41.self_attn.v_proj", "language_model.model.layers.41.self_attn.o_proj", "language_model.model.layers.41.mlp.gate_proj", "language_model.model.layers.41.mlp.up_proj", "language_model.model.layers.41.mlp.down_proj", "language_model.model.layers.42.self_attn.q_proj", "language_model.model.layers.42.self_attn.k_proj", "language_model.model.layers.42.self_attn.v_proj", "language_model.model.layers.42.self_attn.o_proj", "language_model.model.layers.42.mlp.gate_proj", "language_model.model.layers.42.mlp.up_proj", "language_model.model.layers.42.mlp.down_proj", "language_model.model.layers.43.cross_attn.q_proj", "language_model.model.layers.43.cross_attn.k_proj", "language_model.model.layers.43.cross_attn.v_proj", "language_model.model.layers.43.cross_attn.o_proj", "language_model.model.layers.43.mlp.gate_proj", "language_model.model.layers.43.mlp.up_proj", "language_model.model.layers.43.mlp.down_proj", "language_model.model.layers.44.self_attn.q_proj", "language_model.model.layers.44.self_attn.k_proj", "language_model.model.layers.44.self_attn.v_proj", "language_model.model.layers.44.self_attn.o_proj", "language_model.model.layers.44.mlp.gate_proj", "language_model.model.layers.44.mlp.up_proj", "language_model.model.layers.44.mlp.down_proj", "language_model.model.layers.45.self_attn.q_proj", "language_model.model.layers.45.self_attn.k_proj", "language_model.model.layers.45.self_attn.v_proj", "language_model.model.layers.45.self_attn.o_proj", "language_model.model.layers.45.mlp.gate_proj", "language_model.model.layers.45.mlp.up_proj", "language_model.model.layers.45.mlp.down_proj", "language_model.model.layers.46.self_attn.q_proj", "language_model.model.layers.46.self_attn.k_proj", "language_model.model.layers.46.self_attn.v_proj", "language_model.model.layers.46.self_attn.o_proj", "language_model.model.layers.46.mlp.gate_proj", "language_model.model.layers.46.mlp.up_proj", "language_model.model.layers.46.mlp.down_proj", "language_model.model.layers.47.self_attn.q_proj", "language_model.model.layers.47.self_attn.k_proj", "language_model.model.layers.47.self_attn.v_proj", "language_model.model.layers.47.self_attn.o_proj", "language_model.model.layers.47.mlp.gate_proj", "language_model.model.layers.47.mlp.up_proj", "language_model.model.layers.47.mlp.down_proj", "language_model.model.layers.48.cross_attn.q_proj", "language_model.model.layers.48.cross_attn.k_proj", "language_model.model.layers.48.cross_attn.v_proj", "language_model.model.layers.48.cross_attn.o_proj", "language_model.model.layers.48.mlp.gate_proj", "language_model.model.layers.48.mlp.up_proj", "language_model.model.layers.48.mlp.down_proj", "language_model.model.layers.49.self_attn.q_proj", "language_model.model.layers.49.self_attn.k_proj", "language_model.model.layers.49.self_attn.v_proj", "language_model.model.layers.49.self_attn.o_proj", "language_model.model.layers.49.mlp.gate_proj", "language_model.model.layers.49.mlp.up_proj", "language_model.model.layers.49.mlp.down_proj", "language_model.model.layers.50.self_attn.q_proj", "language_model.model.layers.50.self_attn.k_proj", "language_model.model.layers.50.self_attn.v_proj", "language_model.model.layers.50.self_attn.o_proj", "language_model.model.layers.50.mlp.gate_proj", "language_model.model.layers.50.mlp.up_proj", "language_model.model.layers.50.mlp.down_proj", "language_model.model.layers.51.self_attn.q_proj", "language_model.model.layers.51.self_attn.k_proj", "language_model.model.layers.51.self_attn.v_proj", "language_model.model.layers.51.self_attn.o_proj", "language_model.model.layers.51.mlp.gate_proj", "language_model.model.layers.51.mlp.up_proj", "language_model.model.layers.51.mlp.down_proj", "language_model.model.layers.52.self_attn.q_proj", "language_model.model.layers.52.self_attn.k_proj", "language_model.model.layers.52.self_attn.v_proj", "language_model.model.layers.52.self_attn.o_proj", "language_model.model.layers.52.mlp.gate_proj", "language_model.model.layers.52.mlp.up_proj", "language_model.model.layers.52.mlp.down_proj", "language_model.model.layers.53.cross_attn.q_proj", "language_model.model.layers.53.cross_attn.k_proj", "language_model.model.layers.53.cross_attn.v_proj", "language_model.model.layers.53.cross_attn.o_proj", "language_model.model.layers.53.mlp.gate_proj", "language_model.model.layers.53.mlp.up_proj", "language_model.model.layers.53.mlp.down_proj", "language_model.model.layers.54.self_attn.q_proj", "language_model.model.layers.54.self_attn.k_proj", "language_model.model.layers.54.self_attn.v_proj", "language_model.model.layers.54.self_attn.o_proj", "language_model.model.layers.54.mlp.gate_proj", "language_model.model.layers.54.mlp.up_proj", "language_model.model.layers.54.mlp.down_proj", "language_model.model.layers.55.self_attn.q_proj", "language_model.model.layers.55.self_attn.k_proj", "language_model.model.layers.55.self_attn.v_proj", "language_model.model.layers.55.self_attn.o_proj", "language_model.model.layers.55.mlp.gate_proj", "language_model.model.layers.55.mlp.up_proj", "language_model.model.layers.55.mlp.down_proj", "language_model.model.layers.56.self_attn.q_proj", "language_model.model.layers.56.self_attn.k_proj", "language_model.model.layers.56.self_attn.v_proj", "language_model.model.layers.56.self_attn.o_proj", "language_model.model.layers.56.mlp.gate_proj", "language_model.model.layers.56.mlp.up_proj", "language_model.model.layers.56.mlp.down_proj", "language_model.model.layers.57.self_attn.q_proj", "language_model.model.layers.57.self_attn.k_proj", "language_model.model.layers.57.self_attn.v_proj", "language_model.model.layers.57.self_attn.o_proj", "language_model.model.layers.57.mlp.gate_proj", "language_model.model.layers.57.mlp.up_proj", "language_model.model.layers.57.mlp.down_proj", "language_model.model.layers.58.cross_attn.q_proj", "language_model.model.layers.58.cross_attn.k_proj", "language_model.model.layers.58.cross_attn.v_proj", "language_model.model.layers.58.cross_attn.o_proj", "language_model.model.layers.58.mlp.gate_proj", "language_model.model.layers.58.mlp.up_proj", "language_model.model.layers.58.mlp.down_proj", "language_model.model.layers.59.self_attn.q_proj", "language_model.model.layers.59.self_attn.k_proj", "language_model.model.layers.59.self_attn.v_proj", "language_model.model.layers.59.self_attn.o_proj", "language_model.model.layers.59.mlp.gate_proj", "language_model.model.layers.59.mlp.up_proj", "language_model.model.layers.59.mlp.down_proj", "language_model.model.layers.60.self_attn.q_proj", "language_model.model.layers.60.self_attn.k_proj", "language_model.model.layers.60.self_attn.v_proj", "language_model.model.layers.60.self_attn.o_proj", "language_model.model.layers.60.mlp.gate_proj", "language_model.model.layers.60.mlp.up_proj", "language_model.model.layers.60.mlp.down_proj", "language_model.model.layers.61.self_attn.q_proj", "language_model.model.layers.61.self_attn.k_proj", "language_model.model.layers.61.self_attn.v_proj", "language_model.model.layers.61.self_attn.o_proj", "language_model.model.layers.61.mlp.gate_proj", "language_model.model.layers.61.mlp.up_proj", "language_model.model.layers.61.mlp.down_proj", "language_model.model.layers.62.self_attn.q_proj", "language_model.model.layers.62.self_attn.k_proj", "language_model.model.layers.62.self_attn.v_proj", "language_model.model.layers.62.self_attn.o_proj", "language_model.model.layers.62.mlp.gate_proj", "language_model.model.layers.62.mlp.up_proj", "language_model.model.layers.62.mlp.down_proj", "language_model.model.layers.63.cross_attn.q_proj", "language_model.model.layers.63.cross_attn.k_proj", "language_model.model.layers.63.cross_attn.v_proj", "language_model.model.layers.63.cross_attn.o_proj", "language_model.model.layers.63.mlp.gate_proj", "language_model.model.layers.63.mlp.up_proj", "language_model.model.layers.63.mlp.down_proj", "language_model.model.layers.64.self_attn.q_proj", "language_model.model.layers.64.self_attn.k_proj", "language_model.model.layers.64.self_attn.v_proj", "language_model.model.layers.64.self_attn.o_proj", "language_model.model.layers.64.mlp.gate_proj", "language_model.model.layers.64.mlp.up_proj", "language_model.model.layers.64.mlp.down_proj", "language_model.model.layers.65.self_attn.q_proj", "language_model.model.layers.65.self_attn.k_proj", "language_model.model.layers.65.self_attn.v_proj", "language_model.model.layers.65.self_attn.o_proj", "language_model.model.layers.65.mlp.gate_proj", "language_model.model.layers.65.mlp.up_proj", "language_model.model.layers.65.mlp.down_proj", "language_model.model.layers.66.self_attn.q_proj", "language_model.model.layers.66.self_attn.k_proj", "language_model.model.layers.66.self_attn.v_proj", "language_model.model.layers.66.self_attn.o_proj", "language_model.model.layers.66.mlp.gate_proj", "language_model.model.layers.66.mlp.up_proj", "language_model.model.layers.66.mlp.down_proj", "language_model.model.layers.67.self_attn.q_proj", "language_model.model.layers.67.self_attn.k_proj", "language_model.model.layers.67.self_attn.v_proj", "language_model.model.layers.67.self_attn.o_proj", "language_model.model.layers.67.mlp.gate_proj", "language_model.model.layers.67.mlp.up_proj", "language_model.model.layers.67.mlp.down_proj", "language_model.model.layers.68.cross_attn.q_proj", "language_model.model.layers.68.cross_attn.k_proj", "language_model.model.layers.68.cross_attn.v_proj", "language_model.model.layers.68.cross_attn.o_proj", "language_model.model.layers.68.mlp.gate_proj", "language_model.model.layers.68.mlp.up_proj", "language_model.model.layers.68.mlp.down_proj", "language_model.model.layers.69.self_attn.q_proj", "language_model.model.layers.69.self_attn.k_proj", "language_model.model.layers.69.self_attn.v_proj", "language_model.model.layers.69.self_attn.o_proj", "language_model.model.layers.69.mlp.gate_proj", "language_model.model.layers.69.mlp.up_proj", "language_model.model.layers.69.mlp.down_proj", "language_model.model.layers.70.self_attn.q_proj", "language_model.model.layers.70.self_attn.k_proj", "language_model.model.layers.70.self_attn.v_proj", "language_model.model.layers.70.self_attn.o_proj", "language_model.model.layers.70.mlp.gate_proj", "language_model.model.layers.70.mlp.up_proj", "language_model.model.layers.70.mlp.down_proj", "language_model.model.layers.71.self_attn.q_proj", "language_model.model.layers.71.self_attn.k_proj", "language_model.model.layers.71.self_attn.v_proj", "language_model.model.layers.71.self_attn.o_proj", "language_model.model.layers.71.mlp.gate_proj", "language_model.model.layers.71.mlp.up_proj", "language_model.model.layers.71.mlp.down_proj", "language_model.model.layers.72.self_attn.q_proj", "language_model.model.layers.72.self_attn.k_proj", "language_model.model.layers.72.self_attn.v_proj", "language_model.model.layers.72.self_attn.o_proj", "language_model.model.layers.72.mlp.gate_proj", "language_model.model.layers.72.mlp.up_proj", "language_model.model.layers.72.mlp.down_proj", "language_model.model.layers.73.cross_attn.q_proj", "language_model.model.layers.73.cross_attn.k_proj", "language_model.model.layers.73.cross_attn.v_proj", "language_model.model.layers.73.cross_attn.o_proj", "language_model.model.layers.73.mlp.gate_proj", "language_model.model.layers.73.mlp.up_proj", "language_model.model.layers.73.mlp.down_proj", "language_model.model.layers.74.self_attn.q_proj", "language_model.model.layers.74.self_attn.k_proj", "language_model.model.layers.74.self_attn.v_proj", "language_model.model.layers.74.self_attn.o_proj", "language_model.model.layers.74.mlp.gate_proj", "language_model.model.layers.74.mlp.up_proj", "language_model.model.layers.74.mlp.down_proj", "language_model.model.layers.75.self_attn.q_proj", "language_model.model.layers.75.self_attn.k_proj", "language_model.model.layers.75.self_attn.v_proj", "language_model.model.layers.75.self_attn.o_proj", "language_model.model.layers.75.mlp.gate_proj", "language_model.model.layers.75.mlp.up_proj", "language_model.model.layers.75.mlp.down_proj", "language_model.model.layers.76.self_attn.q_proj", "language_model.model.layers.76.self_attn.k_proj", "language_model.model.layers.76.self_attn.v_proj", "language_model.model.layers.76.self_attn.o_proj", "language_model.model.layers.76.mlp.gate_proj", "language_model.model.layers.76.mlp.up_proj", "language_model.model.layers.76.mlp.down_proj", "language_model.model.layers.77.self_attn.q_proj", "language_model.model.layers.77.self_attn.k_proj", "language_model.model.layers.77.self_attn.v_proj", "language_model.model.layers.77.self_attn.o_proj", "language_model.model.layers.77.mlp.gate_proj", "language_model.model.layers.77.mlp.up_proj", "language_model.model.layers.77.mlp.down_proj", "language_model.model.layers.78.cross_attn.q_proj", "language_model.model.layers.78.cross_attn.k_proj", "language_model.model.layers.78.cross_attn.v_proj", "language_model.model.layers.78.cross_attn.o_proj", "language_model.model.layers.78.mlp.gate_proj", "language_model.model.layers.78.mlp.up_proj", "language_model.model.layers.78.mlp.down_proj", "language_model.model.layers.79.self_attn.q_proj", "language_model.model.layers.79.self_attn.k_proj", "language_model.model.layers.79.self_attn.v_proj", "language_model.model.layers.79.self_attn.o_proj", "language_model.model.layers.79.mlp.gate_proj", "language_model.model.layers.79.mlp.up_proj", "language_model.model.layers.79.mlp.down_proj", "language_model.model.layers.80.self_attn.q_proj", "language_model.model.layers.80.self_attn.k_proj", "language_model.model.layers.80.self_attn.v_proj", "language_model.model.layers.80.self_attn.o_proj", "language_model.model.layers.80.mlp.gate_proj", "language_model.model.layers.80.mlp.up_proj", "language_model.model.layers.80.mlp.down_proj", "language_model.model.layers.81.self_attn.q_proj", "language_model.model.layers.81.self_attn.k_proj", "language_model.model.layers.81.self_attn.v_proj", "language_model.model.layers.81.self_attn.o_proj", "language_model.model.layers.81.mlp.gate_proj", "language_model.model.layers.81.mlp.up_proj", "language_model.model.layers.81.mlp.down_proj", "language_model.model.layers.82.self_attn.q_proj", "language_model.model.layers.82.self_attn.k_proj", "language_model.model.layers.82.self_attn.v_proj", "language_model.model.layers.82.self_attn.o_proj", "language_model.model.layers.82.mlp.gate_proj", "language_model.model.layers.82.mlp.up_proj", "language_model.model.layers.82.mlp.down_proj", "language_model.model.layers.83.cross_attn.q_proj", "language_model.model.layers.83.cross_attn.k_proj", "language_model.model.layers.83.cross_attn.v_proj", "language_model.model.layers.83.cross_attn.o_proj", "language_model.model.layers.83.mlp.gate_proj", "language_model.model.layers.83.mlp.up_proj", "language_model.model.layers.83.mlp.down_proj", "language_model.model.layers.84.self_attn.q_proj", "language_model.model.layers.84.self_attn.k_proj", "language_model.model.layers.84.self_attn.v_proj", "language_model.model.layers.84.self_attn.o_proj", "language_model.model.layers.84.mlp.gate_proj", "language_model.model.layers.84.mlp.up_proj", "language_model.model.layers.84.mlp.down_proj", "language_model.model.layers.85.self_attn.q_proj", "language_model.model.layers.85.self_attn.k_proj", "language_model.model.layers.85.self_attn.v_proj", "language_model.model.layers.85.self_attn.o_proj", "language_model.model.layers.85.mlp.gate_proj", "language_model.model.layers.85.mlp.up_proj", "language_model.model.layers.85.mlp.down_proj", "language_model.model.layers.86.self_attn.q_proj", "language_model.model.layers.86.self_attn.k_proj", "language_model.model.layers.86.self_attn.v_proj", "language_model.model.layers.86.self_attn.o_proj", "language_model.model.layers.86.mlp.gate_proj", "language_model.model.layers.86.mlp.up_proj", "language_model.model.layers.86.mlp.down_proj", "language_model.model.layers.87.self_attn.q_proj", "language_model.model.layers.87.self_attn.k_proj", "language_model.model.layers.87.self_attn.v_proj", "language_model.model.layers.87.self_attn.o_proj", "language_model.model.layers.87.mlp.gate_proj", "language_model.model.layers.87.mlp.up_proj", "language_model.model.layers.87.mlp.down_proj", "language_model.model.layers.88.cross_attn.q_proj", "language_model.model.layers.88.cross_attn.k_proj", "language_model.model.layers.88.cross_attn.v_proj", "language_model.model.layers.88.cross_attn.o_proj", "language_model.model.layers.88.mlp.gate_proj", "language_model.model.layers.88.mlp.up_proj", "language_model.model.layers.88.mlp.down_proj", "language_model.model.layers.89.self_attn.q_proj", "language_model.model.layers.89.self_attn.k_proj", "language_model.model.layers.89.self_attn.v_proj", "language_model.model.layers.89.self_attn.o_proj", "language_model.model.layers.89.mlp.gate_proj", "language_model.model.layers.89.mlp.up_proj", "language_model.model.layers.89.mlp.down_proj", "language_model.model.layers.90.self_attn.q_proj", "language_model.model.layers.90.self_attn.k_proj", "language_model.model.layers.90.self_attn.v_proj", "language_model.model.layers.90.self_attn.o_proj", "language_model.model.layers.90.mlp.gate_proj", "language_model.model.layers.90.mlp.up_proj", "language_model.model.layers.90.mlp.down_proj", "language_model.model.layers.91.self_attn.q_proj", "language_model.model.layers.91.self_attn.k_proj", "language_model.model.layers.91.self_attn.v_proj", "language_model.model.layers.91.self_attn.o_proj", "language_model.model.layers.91.mlp.gate_proj", "language_model.model.layers.91.mlp.up_proj", "language_model.model.layers.91.mlp.down_proj", "language_model.model.layers.92.self_attn.q_proj", "language_model.model.layers.92.self_attn.k_proj", "language_model.model.layers.92.self_attn.v_proj", "language_model.model.layers.92.self_attn.o_proj", "language_model.model.layers.92.mlp.gate_proj", "language_model.model.layers.92.mlp.up_proj", "language_model.model.layers.92.mlp.down_proj", "language_model.model.layers.93.cross_attn.q_proj", "language_model.model.layers.93.cross_attn.k_proj", "language_model.model.layers.93.cross_attn.v_proj", "language_model.model.layers.93.cross_attn.o_proj", "language_model.model.layers.93.mlp.gate_proj", "language_model.model.layers.93.mlp.up_proj", "language_model.model.layers.93.mlp.down_proj", "language_model.model.layers.94.self_attn.q_proj", "language_model.model.layers.94.self_attn.k_proj", "language_model.model.layers.94.self_attn.v_proj", "language_model.model.layers.94.self_attn.o_proj", "language_model.model.layers.94.mlp.gate_proj", "language_model.model.layers.94.mlp.up_proj", "language_model.model.layers.94.mlp.down_proj", "language_model.model.layers.95.self_attn.q_proj", "language_model.model.layers.95.self_attn.k_proj", "language_model.model.layers.95.self_attn.v_proj", "language_model.model.layers.95.self_attn.o_proj", "language_model.model.layers.95.mlp.gate_proj", "language_model.model.layers.95.mlp.up_proj", "language_model.model.layers.95.mlp.down_proj", "language_model.model.layers.96.self_attn.q_proj", "language_model.model.layers.96.self_attn.k_proj", "language_model.model.layers.96.self_attn.v_proj", "language_model.model.layers.96.self_attn.o_proj", "language_model.model.layers.96.mlp.gate_proj", "language_model.model.layers.96.mlp.up_proj", "language_model.model.layers.96.mlp.down_proj", "language_model.model.layers.97.self_attn.q_proj", "language_model.model.layers.97.self_attn.k_proj", "language_model.model.layers.97.self_attn.v_proj", "language_model.model.layers.97.self_attn.o_proj", "language_model.model.layers.97.mlp.gate_proj", "language_model.model.layers.97.mlp.up_proj", "language_model.model.layers.97.mlp.down_proj", "language_model.model.layers.98.cross_attn.q_proj", "language_model.model.layers.98.cross_attn.k_proj", "language_model.model.layers.98.cross_attn.v_proj", "language_model.model.layers.98.cross_attn.o_proj", "language_model.model.layers.98.mlp.gate_proj", "language_model.model.layers.98.mlp.up_proj", "language_model.model.layers.98.mlp.down_proj", "language_model.model.layers.99.self_attn.q_proj", "language_model.model.layers.99.self_attn.k_proj", "language_model.model.layers.99.self_attn.v_proj", "language_model.model.layers.99.self_attn.o_proj", "language_model.model.layers.99.mlp.gate_proj", "language_model.model.layers.99.mlp.up_proj", "language_model.model.layers.99.mlp.down_proj", "language_model.lm_head", "multi_modal_projector" ], "registry_requires_subclass": false, "sparsity_structure": "unstructured", "targets": [ "language_model.model.layers.0.self_attn.q_proj", "language_model.model.layers.0.self_attn.k_proj", "language_model.model.layers.0.self_attn.v_proj", "language_model.model.layers.1.self_attn.q_proj", "language_model.model.layers.1.self_attn.k_proj" ] } }, "text_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 128000, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "cross_attention_layers": [ 3, 8, 13, 18, 23, 28, 33, 38, 43, 48, 53, 58, 63, 68, 73, 78, 83, 88, 93, 98 ], "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": [ 128001, 128008, 128009 ], "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 8192, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 28672, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 131072, "min_length": 0, "model_type": "mllama_text_model", "no_repeat_ngram_size": 0, "num_attention_heads": 64, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 100, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 128004, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 128256 }, "torch_dtype": "bfloat16", "transformers_version": "4.46.1", "vision_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_heads": 16, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1280, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 560, "initializer_range": 0.02, "intermediate_layers_indices": [ 3, 7, 15, 23, 30 ], "intermediate_size": 5120, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_num_tiles": 4, "min_length": 0, "model_type": "mllama_vision_model", "no_repeat_ngram_size": 0, "norm_eps": 1e-05, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_global_layers": 8, "num_hidden_layers": 32, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "supported_aspect_ratios": [ [ 1, 1 ], [ 1, 2 ], [ 1, 3 ], [ 1, 4 ], [ 2, 1 ], [ 2, 2 ], [ 3, 1 ], [ 4, 1 ] ], "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "vision_output_dim": 7680 } }