config.json

{
  "_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
  "architectures": [
    "MllamaForConditionalGeneration"
  ],
  "image_token_index": 128256,
  "model_type": "mllama",
  "text_config": {
    "eos_token_id": [
      128001,
      128008,
      128009
    ],
    "model_type": "mllama_text_model",
    "rope_scaling": {
      "factor": 8.0,
      "high_freq_factor": 4.0,
      "low_freq_factor": 1.0,
      "original_max_position_embeddings": 8192,
      "rope_type": "llama3"
    },
    "torch_dtype": "bfloat16"
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.47.1",
  "vision_config": {
    "image_size": 560,
    "model_type": "mllama_vision_model",
    "torch_dtype": "bfloat16"
  }
}