config.json

{
  "model_type": "baguettotron_vlm",
  "vit_model_id": "OpenGVLab/InternViT-300M-448px-V2_5",
  "llm_model_id": "PleIAs/Baguettotron",
  "vit_hidden": 1024,
  "vit_tokens": 1024,
  "llm_hidden": 576,
  "num_visual_tokens": 256,
  "unshuffle_factor": 2,
  "image_token": "<image>",
  "chat_style": "base",
  "stage": 1,
  "torch_dtype": "bfloat16",
  "bos_token_id": 1,
  "eos_token_id": [
    2,
    65492
  ],
  "pad_token_id": 3,
  "tie_word_embeddings": false,
  "auto_map": {
    "AutoConfig": "configuration_baguettotron_vlm.BaguettotronVLMConfig",
    "AutoModelForImageTextToText": "modeling_baguettotron_vlm.BaguettotronVLMForConditionalGeneration",
    "AutoProcessor": "processing_baguettotron_vlm.BaguettotronVLMProcessor"
  }
}