config.json

{
  "architectures": [
    "Llamavision"
  ],
  "auto_map": {
    "AutoConfig": "configuration_llamavision.LlamavisionConfig",
    "AutoModelForCausalLM": "modeling_llamavision.Llamavision"
  },
  "model_type": "llamavision",
  "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": "float16",
    "vocab_size": 128256
  },
  "torch_dtype": "float16",
  "transformers_version": "4.43.1",
  "vision_config": {
    "_name_or_path": "google/siglip-so400m-patch14-384",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14
  }
}