config.json

{
  "_name_or_path": "StanfordAIMI/chexagent-v1",
  "architectures": [
    "CheXagentForConditionalGeneration"
  ],
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "chexagent",
  "num_max_images": 2,
  "num_query_tokens": 128,
  "qformer_config": {
    "model_type": "chexagent_qformer",
    "vocab_size": 30523
  },
  "text_config": {
    "_name_or_path": "mistralai/Mistral-7B-v0.1",
    "architectures": [
      "MistralForCausalLM"
    ],
    "attention_bias": false,
    "bos_token_id": 1,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 32768,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "pad_token_id": null,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "sliding_window": 4096,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "vocab_size": 32000
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.35.2",
  "use_decoder_only_language_model": true,
  "vision_config": {
    "image_size": 448,
    "model_type": "chexagent_vision_model",
    "num_hidden_layers": 40
  }
}