{ "_name_or_path": "deepseek-ai/DeepSeek-OCR", "model_type": "deepseekocr", "candidate_resolutions": [[1024, 1024]], "global_view_pos": "head", "architectures": ["DeepseekOCRForCausalLM"], "auto_map": { "AutoConfig": "configuration_deepseekocr.DeepseekOCRConfig", "AutoModel": "modeling_deepseekocr.DeepseekOCRForCausalLM" }, "language_config": { "architectures": ["DeepseekV2ForCausalLM"], "auto_map": { "AutoConfig": "configuration_deepseekv2.DeepseekV2Config", "AutoModel": "modeling_deepseek.DeepseekV2Model", "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM" }, "bos_token_id": 0, "eos_token_id": 1, "first_k_dense_replace": 1, "hidden_size": 1280, "intermediate_size": 6848, "kv_lora_rank": null, "lm_head": true, "max_position_embeddings": 8192, "moe_intermediate_size": 896, "n_group": 1, "n_routed_experts": 64, "n_shared_experts": 2, "num_attention_heads": 10, "num_experts_per_tok": 6, "num_hidden_layers": 12, "num_key_value_heads": 10, "q_lora_rank": null, "qk_nope_head_dim": 0, "qk_rope_head_dim": 0, "rm_head": false, "topk_group": 1, "topk_method": "greedy", "torch_dtype": "bfloat16", "use_mla": false, "v_head_dim": 0, "vocab_size": 129280 }, "projector_config": { "input_dim": 2048, "model_type": "mlp_projector", "n_embed": 1280, "projector_type": "linear" }, "tile_tag": "2D", "torch_dtype": "bfloat16", "transformers_version": "4.46.3", "vision_config": { "image_size": 1024, "mlp_ratio": 3.7362, "model_name": "deeplip_b_l", "model_type": "vision", "width": { "clip-l-14-224": { "heads": 16, "image_size": 224, "layers": 24, "patch_size": 14, "width": 1024 }, "sam_vit_b": { "downsample_channels": [512, 1024], "global_attn_indexes": [2, 5, 8, 11], "heads": 12, "layers": 12, "width": 768 } } }, "bos_token_id": 0, "eos_token_id": 1, "first_k_dense_replace": 1, "hidden_size": 1280, "intermediate_size": 6848, "kv_lora_rank": null, "lm_head": true, "max_position_embeddings": 8192, "moe_intermediate_size": 896, "n_group": 1, "n_routed_experts": 64, "n_shared_experts": 2, "num_attention_heads": 10, "num_experts_per_tok": 6, "num_hidden_layers": 12, "num_key_value_heads": 10, "q_lora_rank": null, "qk_nope_head_dim": 0, "qk_rope_head_dim": 0, "rm_head": false, "topk_group": 1, "topk_method": "greedy", "use_mla": false, "v_head_dim": 0, "vocab_size": 129280 }