{
  "architectures": [
    "MonkeyOCRv2VisionTransformer"
  ],
  "auto_map": {
    "AutoConfig": "configuration_monkeyocrv2vit.MonkeyOCRv2VisionConfig",
    "AutoModel": "modeling_monkeyocrv2_vision.MonkeyOCRv2VisionTransformer"
  },
  "vision_attn_implementation": "flash_attention_2",
  "dtype": "bfloat16",
  "embed_dim": 768,
  "gradient_checkpointing": false,
  "hidden_size": 1024,
  "init_merger_std": 0.02,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "is_causal": false,
  "model_type": "monkeyocr_vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "pad_token_id": 151643,
  "patch_size": 14,
  "post_norm": true,
  "rms_norm_eps": 1e-05,
  "spatial_merge_size": 2,
  "temporal_patch_size": 1,
  "use_bias": false
}