config.json

{
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_seq_length": 576,
  "image_token_index": 32000,
  "model_type": "llava_next",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "head_dim": 4,
    "hidden_act": "silu",
    "hidden_size": 16,
    "initializer_range": 0.02,
    "intermediate_size": 32,
    "max_position_embeddings": 2048,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "num_key_value_heads": 2,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "use_cache": true,
    "vocab_size": 32005
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.56.0.dev0",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 16,
    "image_size": 336,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 32,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 4,
    "num_channels": 3,
    "num_hidden_layers": 2,
    "patch_size": 14,
    "projection_dim": 8
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}