config.json

{
  "_name_or_path": "./unsloth/Llama-3.2-90B-Vision-Instruct",
  "architectures": [
    "MllamaForConditionalGeneration"
  ],
  "image_token_index": 128256,
  "model_type": "mllama",
  "text_config": {
    "cross_attention_layers": [
      3,
      8,
      13,
      18,
      23,
      28,
      33,
      38,
      43,
      48,
      53,
      58,
      63,
      68,
      73,
      78,
      83,
      88,
      93,
      98
    ],
    "eos_token_id": [
      128001,
      128008,
      128009
    ],
    "hidden_size": 8192,
    "intermediate_size": 28672,
    "model_type": "mllama_text_model",
    "num_attention_heads": 64,
    "num_hidden_layers": 100,
    "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": "4.47.0",
  "vision_config": {
    "image_size": 560,
    "model_type": "mllama_vision_model",
    "torch_dtype": "bfloat16"
  }
}