a-plus/config.json

{
  "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": 200000,
    "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": {}
  }
}