{
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "hidden_size": 4096,
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_seq_length": 576,
  "image_token_index": 128256,
  "keys_to_ignore_at_inference": [
    "past_key_values"
  ],
  "mha2mla": {
    "is_baseline": false,
    "is_gqa2mha2mla": false,
    "low_rank": 128,
    "multimodal_rope_section_for_mla": null,
    "partial_rope_version": "mkl",
    "peft_train": "v2",
    "qk_tensor_path": "mkl/llava_next/llava_next-ranks.pth",
    "rope_dim_for_mla": 32,
    "stage1_path": "cnxup/LLaVA-NeXT-8B-MLA-stage1-rope32",
    "svd_init_method": "joint",
    "svd_init_weight_path": "LLaVA-NeXT-8B-rope32-d_kv_128.pt",
    "svd_split_modal": true,
    "uniform_start_point": 0
  },
  "model_type": "llava_next",
  "multimodal_projector_bias": true,
  "pad_token_id": 128257,
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": 128009,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000.0,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 128320
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_image_newline_parameter": true,
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 336,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768,
    "torch_dtype": "bfloat16",
    "vocab_size": 32000
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}