config.json

{
  "architectures": [
    "DotsOCRForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_dots.DotsOCRConfig",
    "AutoModelForCausalLM": "modeling_dots_ocr.DotsOCRForCausalLM"
  },
  "hidden_act": "silu",
  "hidden_size": 1536,
  "image_token_id": 151665,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "dots_ocr",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "attn_implementation": "flash_attention_2",
    "embed_dim": 1536,
    "gradient_checkpointing": false,
    "hidden_size": 1536,
    "init_merger_std": 0.02,
    "initializer_range": 0.02,
    "intermediate_size": 4224,
    "is_causal": false,
    "model_type": "dots_vit",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 42,
    "patch_size": 14,
    "post_norm": true,
    "rms_norm_eps": 1e-05,
    "spatial_merge_size": 2,
    "temporal_patch_size": 1,
    "use_bias": false
  },
  "vocab_size": 151936
}