{ "alignment_activation_fn": "swiglu", "alignment_intermediate_size": 12288, "architectures": [ "Cohere2VisionForConditionalGeneration" ], "downsample_factor": 2, "dtype": "bfloat16", "enable_adapter_layer_norm": false, "image_token": 255031, "image_token_id": 255031, "max_splits_per_img": 12, "model_type": "cohere2_vision", "text_config": { "_sliding_window_pattern": 4, "architectures": [ "Cohere2MoeForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 2, "expert_selection_fn": "sigmoid", "first_k_dense_replace": 0, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-05, "layer_switch": 4, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "logit_scale": 1.0, "max_position_embeddings": 5000000, "model_type": "cohere2_moe", "norm_topk_prob": true, "norm_type": "layer_norm", "num_attention_heads": 128, "num_experts": 128, "num_experts_per_tok": 8, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_shared_experts": 4, "order_of_interleaved_layers": "local_attn_first", "position_embedding_type": "rope_gptj", "prefix_dense_intermediate_size": 16384, "prefix_dense_sliding_window_pattern": 1, "rms_norm_eps": null, "rope_scaling": null, "rope_theta": 50000, "rotary_pct": 1.0, "shared_expert_combination_strategy": "average", "sliding_window": 4096, "transformer_block_type": "parallel", "use_cache": true, "use_embedding_sharing": true, "use_gated_activation": true, "use_parallel_embedding": false, "use_qk_norm": false, "vocab_size": 262144 }, "transformers_version": "4.56.2.4", "vision_config": { "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 512, "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": 16, "vision_use_head": false }, "vision_feature_layer": -1, "vision_feature_select_strategy": "full", "quantization_config": { "config_groups": { "group_0": { "targets": [ "Linear" ], "weights": { "num_bits": 4, "type": "float", "symmetric": true, "group_size": 16, "strategy": "tensor_group", "block_structure": null, "dynamic": false, "actorder": null, "scale_dtype": "torch.float8_e4m3fn", "zp_dtype": null, "observer": "memoryless_minmax", "observer_kwargs": {} }, "input_activations": { "num_bits": 4, "type": "float", "symmetric": true, "group_size": 16, "strategy": "tensor_group", "block_structure": null, "dynamic": "local", "actorder": null, "scale_dtype": null, "zp_dtype": null, "observer": "static_minmax", "observer_kwargs": {} }, "output_activations": null, "format": null } }, "kv_cache_scheme": null, "format": "nvfp4-pack-quantized", "quantization_status": "compressed", "global_compression_ratio": null, "ignore": [ "model.language_model.layers.0.mlp.gate", "model.language_model.layers.0.self_attn.k_proj", "model.language_model.layers.0.self_attn.o_proj", "model.language_model.layers.0.self_attn.q_proj", "model.language_model.layers.0.self_attn.v_proj", "model.language_model.layers.1.mlp.gate", "model.language_model.layers.1.self_attn.k_proj", "model.language_model.layers.1.self_attn.o_proj", "model.language_model.layers.1.self_attn.q_proj", "model.language_model.layers.1.self_attn.v_proj", "model.language_model.layers.10.mlp.gate", "model.language_model.layers.10.self_attn.k_proj", "model.language_model.layers.10.self_attn.o_proj", "model.language_model.layers.10.self_attn.q_proj", "model.language_model.layers.10.self_attn.v_proj", "model.language_model.layers.11.mlp.gate", "model.language_model.layers.11.self_attn.k_proj", "model.language_model.layers.11.self_attn.o_proj", "model.language_model.layers.11.self_attn.q_proj", "model.language_model.layers.11.self_attn.v_proj", "model.language_model.layers.12.mlp.gate", "model.language_model.layers.12.self_attn.k_proj", "model.language_model.layers.12.self_attn.o_proj", "model.language_model.layers.12.self_attn.q_proj", "model.language_model.layers.12.self_attn.v_proj", "model.language_model.layers.13.mlp.gate", "model.language_model.layers.13.self_attn.k_proj", "model.language_model.layers.13.self_attn.o_proj", "model.language_model.layers.13.self_attn.q_proj", "model.language_model.layers.13.self_attn.v_proj", "model.language_model.layers.14.mlp.gate", "model.language_model.layers.14.self_attn.k_proj", "model.language_model.layers.14.self_attn.o_proj", "model.language_model.layers.14.self_attn.q_proj", "model.language_model.layers.14.self_attn.v_proj", "model.language_model.layers.15.mlp.gate", "model.language_model.layers.15.self_attn.k_proj", "model.language_model.layers.15.self_attn.o_proj", "model.language_model.layers.15.self_attn.q_proj", "model.language_model.layers.15.self_attn.v_proj", "model.language_model.layers.16.mlp.gate", "model.language_model.layers.16.self_attn.k_proj", "model.language_model.layers.16.self_attn.o_proj", "model.language_model.layers.16.self_attn.q_proj", "model.language_model.layers.16.self_attn.v_proj", "model.language_model.layers.17.mlp.gate", "model.language_model.layers.17.self_attn.k_proj", "model.language_model.layers.17.self_attn.o_proj", "model.language_model.layers.17.self_attn.q_proj", "model.language_model.layers.17.self_attn.v_proj", "model.language_model.layers.18.mlp.gate", "model.language_model.layers.18.self_attn.k_proj", "model.language_model.layers.18.self_attn.o_proj", "model.language_model.layers.18.self_attn.q_proj", "model.language_model.layers.18.self_attn.v_proj", "model.language_model.layers.19.mlp.gate", "model.language_model.layers.19.self_attn.k_proj", "model.language_model.layers.19.self_attn.o_proj", "model.language_model.layers.19.self_attn.q_proj", "model.language_model.layers.19.self_attn.v_proj", "model.language_model.layers.2.mlp.gate", "model.language_model.layers.2.self_attn.k_proj", "model.language_model.layers.2.self_attn.o_proj", "model.language_model.layers.2.self_attn.q_proj", "model.language_model.layers.2.self_attn.v_proj", "model.language_model.layers.20.mlp.gate", "model.language_model.layers.20.self_attn.k_proj", "model.language_model.layers.20.self_attn.o_proj", "model.language_model.layers.20.self_attn.q_proj", "model.language_model.layers.20.self_attn.v_proj", "model.language_model.layers.21.mlp.gate", "model.language_model.layers.21.self_attn.k_proj", "model.language_model.layers.21.self_attn.o_proj", "model.language_model.layers.21.self_attn.q_proj", "model.language_model.layers.21.self_attn.v_proj", "model.language_model.layers.22.mlp.gate", "model.language_model.layers.22.self_attn.k_proj", "model.language_model.layers.22.self_attn.o_proj", "model.language_model.layers.22.self_attn.q_proj", "model.language_model.layers.22.self_attn.v_proj", "model.language_model.layers.23.mlp.gate", "model.language_model.layers.23.self_attn.k_proj", "model.language_model.layers.23.self_attn.o_proj", "model.language_model.layers.23.self_attn.q_proj", "model.language_model.layers.23.self_attn.v_proj", "model.language_model.layers.24.mlp.gate", "model.language_model.layers.24.self_attn.k_proj", "model.language_model.layers.24.self_attn.o_proj", "model.language_model.layers.24.self_attn.q_proj", "model.language_model.layers.24.self_attn.v_proj", "model.language_model.layers.25.mlp.gate", "model.language_model.layers.25.self_attn.k_proj", "model.language_model.layers.25.self_attn.o_proj", "model.language_model.layers.25.self_attn.q_proj", "model.language_model.layers.25.self_attn.v_proj", "model.language_model.layers.26.mlp.gate", "model.language_model.layers.26.self_attn.k_proj", "model.language_model.layers.26.self_attn.o_proj", "model.language_model.layers.26.self_attn.q_proj", "model.language_model.layers.26.self_attn.v_proj", "model.language_model.layers.27.mlp.gate", "model.language_model.layers.27.self_attn.k_proj", "model.language_model.layers.27.self_attn.o_proj", "model.language_model.layers.27.self_attn.q_proj", "model.language_model.layers.27.self_attn.v_proj", "model.language_model.layers.28.mlp.gate", "model.language_model.layers.28.self_attn.k_proj", "model.language_model.layers.28.self_attn.o_proj", "model.language_model.layers.28.self_attn.q_proj", "model.language_model.layers.28.self_attn.v_proj", "model.language_model.layers.29.mlp.gate", "model.language_model.layers.29.self_attn.k_proj", "model.language_model.layers.29.self_attn.o_proj", "model.language_model.layers.29.self_attn.q_proj", "model.language_model.layers.29.self_attn.v_proj", "model.language_model.layers.3.mlp.gate", "model.language_model.layers.3.self_attn.k_proj", "model.language_model.layers.3.self_attn.o_proj", "model.language_model.layers.3.self_attn.q_proj", "model.language_model.layers.3.self_attn.v_proj", "model.language_model.layers.30.mlp.gate", "model.language_model.layers.30.self_attn.k_proj", "model.language_model.layers.30.self_attn.o_proj", "model.language_model.layers.30.self_attn.q_proj", "model.language_model.layers.30.self_attn.v_proj", "model.language_model.layers.31.mlp.gate", "model.language_model.layers.31.self_attn.k_proj", "model.language_model.layers.31.self_attn.o_proj", "model.language_model.layers.31.self_attn.q_proj", "model.language_model.layers.31.self_attn.v_proj", "model.language_model.layers.4.mlp.gate", "model.language_model.layers.4.self_attn.k_proj", "model.language_model.layers.4.self_attn.o_proj", "model.language_model.layers.4.self_attn.q_proj", "model.language_model.layers.4.self_attn.v_proj", "model.language_model.layers.5.mlp.gate", "model.language_model.layers.5.self_attn.k_proj", "model.language_model.layers.5.self_attn.o_proj", "model.language_model.layers.5.self_attn.q_proj", "model.language_model.layers.5.self_attn.v_proj", "model.language_model.layers.6.mlp.gate", "model.language_model.layers.6.self_attn.k_proj", "model.language_model.layers.6.self_attn.o_proj", "model.language_model.layers.6.self_attn.q_proj", "model.language_model.layers.6.self_attn.v_proj", "model.language_model.layers.7.mlp.gate", "model.language_model.layers.7.self_attn.k_proj", "model.language_model.layers.7.self_attn.o_proj", "model.language_model.layers.7.self_attn.q_proj", "model.language_model.layers.7.self_attn.v_proj", "model.language_model.layers.8.mlp.gate", "model.language_model.layers.8.self_attn.k_proj", "model.language_model.layers.8.self_attn.o_proj", "model.language_model.layers.8.self_attn.q_proj", "model.language_model.layers.8.self_attn.v_proj", "model.language_model.layers.9.mlp.gate", "model.language_model.layers.9.self_attn.k_proj", "model.language_model.layers.9.self_attn.o_proj", "model.language_model.layers.9.self_attn.q_proj", "model.language_model.layers.9.self_attn.v_proj", "model.multi_modal_projector.linear_1", "model.multi_modal_projector.linear_2", "model.vision_tower.vision_model.embeddings.patch_embedding", "model.vision_tower.vision_model.embeddings.position_embedding", "model.vision_tower.vision_model.encoder.layers.0.layer_norm1", "model.vision_tower.vision_model.encoder.layers.0.layer_norm2", "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.1.layer_norm1", "model.vision_tower.vision_model.encoder.layers.1.layer_norm2", "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.10.layer_norm1", "model.vision_tower.vision_model.encoder.layers.10.layer_norm2", "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.11.layer_norm1", "model.vision_tower.vision_model.encoder.layers.11.layer_norm2", "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.12.layer_norm1", "model.vision_tower.vision_model.encoder.layers.12.layer_norm2", "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.13.layer_norm1", "model.vision_tower.vision_model.encoder.layers.13.layer_norm2", "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.14.layer_norm1", "model.vision_tower.vision_model.encoder.layers.14.layer_norm2", "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.15.layer_norm1", "model.vision_tower.vision_model.encoder.layers.15.layer_norm2", "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.16.layer_norm1", "model.vision_tower.vision_model.encoder.layers.16.layer_norm2", "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.17.layer_norm1", "model.vision_tower.vision_model.encoder.layers.17.layer_norm2", "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.18.layer_norm1", "model.vision_tower.vision_model.encoder.layers.18.layer_norm2", "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.19.layer_norm1", "model.vision_tower.vision_model.encoder.layers.19.layer_norm2", "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.2.layer_norm1", "model.vision_tower.vision_model.encoder.layers.2.layer_norm2", "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.20.layer_norm1", "model.vision_tower.vision_model.encoder.layers.20.layer_norm2", "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.21.layer_norm1", "model.vision_tower.vision_model.encoder.layers.21.layer_norm2", "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.22.layer_norm1", "model.vision_tower.vision_model.encoder.layers.22.layer_norm2", "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.23.layer_norm1", "model.vision_tower.vision_model.encoder.layers.23.layer_norm2", "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.24.layer_norm1", "model.vision_tower.vision_model.encoder.layers.24.layer_norm2", "model.vision_tower.vision_model.encoder.layers.24.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.25.layer_norm1", "model.vision_tower.vision_model.encoder.layers.25.layer_norm2", "model.vision_tower.vision_model.encoder.layers.25.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.26.layer_norm1", "model.vision_tower.vision_model.encoder.layers.26.layer_norm2", "model.vision_tower.vision_model.encoder.layers.26.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.3.layer_norm1", "model.vision_tower.vision_model.encoder.layers.3.layer_norm2", "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.4.layer_norm1", "model.vision_tower.vision_model.encoder.layers.4.layer_norm2", "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.5.layer_norm1", "model.vision_tower.vision_model.encoder.layers.5.layer_norm2", "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.6.layer_norm1", "model.vision_tower.vision_model.encoder.layers.6.layer_norm2", "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.7.layer_norm1", "model.vision_tower.vision_model.encoder.layers.7.layer_norm2", "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.8.layer_norm1", "model.vision_tower.vision_model.encoder.layers.8.layer_norm2", "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj", "model.vision_tower.vision_model.encoder.layers.9.layer_norm1", "model.vision_tower.vision_model.encoder.layers.9.layer_norm2", "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1", "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2", "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj", "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj", "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj", "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj", "model.vision_tower.vision_model.post_layernorm" ], "version": "0.15.1.dev6+g077e752", "quant_method": "compressed-tensors", "sparsity_config": {}, "transform_config": {} } }