| { |
| "architectures": [ |
| "DotsOCRForCausalLM" |
| ], |
| "model_type": "dots_ocr", |
| "auto_map": { |
| "AutoConfig": "configuration_dots.DotsOCRConfig", |
| "AutoModelForCausalLM": "modeling_dots_ocr.DotsOCRForCausalLM" |
| }, |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "hidden_act": "silu", |
| "hidden_size": 1536, |
| "initializer_range": 0.02, |
| "intermediate_size": 8960, |
| "max_position_embeddings": 131072, |
| "max_window_layers": 28, |
| "num_attention_heads": 12, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 2, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "sliding_window": 131072, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.0", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936, |
| "image_token_id": 151665, |
| "video_token_id": 151656, |
| "vision_config": { |
| "embed_dim": 1536, |
| "hidden_size": 1536, |
| "intermediate_size": 4224, |
| "num_hidden_layers": 42, |
| "num_attention_heads": 12, |
| "num_channels": 3, |
| "patch_size": 14, |
| "post_norm": true, |
| "rms_norm_eps": 1e-05, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 1, |
| "use_bias": false, |
| "attn_implementation": "flash_attention_2", |
| "init_merger_std": 0.02, |
| "initializer_range": 0.02, |
| "is_causal": false |
| } |
| } |