config.json

{
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_token_index": 128265,
  "model_type": "llava_next",
  "pad_token_id": 128264,
  "projector_hidden_act": "gelu",
  "text_config": {
    "intermediate_size": 14336,
    "max_length": 1536,
    "max_position_embeddings": 1536,
    "model_type": "llama",
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_theta": 500000,
    "vocab_size": 128512
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.40.2",
  "vision_config": {
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "full"
}