{ "architectures": [ "MonkeyOCRv2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_monkeyocrv2.MonkeyOCRv2Config", "AutoModelForCausalLM": "modeling_monkeyocrv2.MonkeyOCRv2ForCausalLM" }, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1024, "image_token_id": 151655, "initializer_range": 0.02, "intermediate_size": 3072, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 40960, "max_window_layers": 28, "model_type": "monkeyocrv2", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 8, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "4.57.1", "use_cache": false, "use_sliding_window": false, "video_token_id": 151656, "vision_config": { "attn_implementation": "flash_attention_2", "dtype": "bfloat16", "embed_dim": 384, "gradient_checkpointing": false, "hidden_size": 1024, "init_merger_std": 0.02, "initializer_range": 0.02, "intermediate_size": 1536, "is_causal": false, "model_type": "monkeyocr_vit", "num_attention_heads": 6, "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 }, "vocab_size": 151936 }