config.json

{
  "architectures": [
    "LlavaForConditionalGeneration"
  ],
  "bos_token_id": 128000,
  "eos_token_id": 128009,
  "ignore_index": -100,
  "image_token_index": 128256,
  "model_type": "llava",
  "pad_token_id": 128258,
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "bos_token_id": 128000,
    "eos_token_id": [
      128001,
      128008,
      128009
    ],
    "intermediate_size": 14336,
    "max_position_embeddings": 131072,
    "model_type": "llama",
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "factor": 8.0,
      "high_freq_factor": 4.0,
      "low_freq_factor": 1.0,
      "original_max_position_embeddings": 8192,
      "rope_type": "llama3"
    },
    "rope_theta": 500000.0,
    "torch_dtype": "bfloat16",
    "vocab_size": 128259
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.3",
  "vision_config": {
    "dropout": 0.0,
    "hidden_size": 1024,
    "image_size": 336,
    "intermediate_size": 4096,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}