config.json

{
  "architectures": [
    "Idefics2ForConditionalGeneration"
  ],
  "image_token_id": 32001,
  "model_type": "idefics2",
  "perceiver_config": {
    "model_type": "idefics2"
  },
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "modules_to_not_convert": ["model.vision_model", "model.connector.modality_projection", "model.connector.perceiver_resampler"],
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "text_config": {
    "max_position_embeddings": 32768,
    "model_type": "mistral",
    "pad_token_id": 0,
    "rms_norm_eps": 1e-05,
    "vocab_size": 32003
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.40.0.dev0",
  "use_cache": true,
  "vision_config": {
    "hidden_size": 1152,
    "image_size": 980,
    "intermediate_size": 4304,
    "model_type": "idefics2",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14
  }
}