{ "architectures": [ "DeepseekOCRForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "modeling_deepseekocr.DeepseekOCRConfig", "AutoModel": "modeling_deepseekocr.DeepseekOCRForCausalLM", "AutoModelForCausalLM": "modeling_deepseekocr.DeepseekOCRForCausalLM", "AutoProcessor": "processing_deepseek_ocr.DeepseekOCRProcessor" }, "bos_token_id": 0, "candidate_resolutions": [ [ 1024, 1024 ] ], "dtype": "bfloat16", "eos_token_id": 1, "ep_size": 1, "first_k_dense_replace": 1, "global_view_pos": "head", "hidden_act": "silu", "hidden_size": 1280, "image_token_index": 128815, "initializer_range": 0.02, "intermediate_size": 6848, "kv_lora_rank": null, "language_config": { "architectures": [ "DeepseekV2ForCausalLM" ], "auto_map": { "AutoConfig": "configuration_deepseek_v2.DeepseekV2Config", "AutoModel": "modeling_deepseekv2.DeepseekV2Model", "AutoModelForCausalLM": "modeling_deepseekv2.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": 32768, "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, "rope_scaling": null, "rope_theta": 1000000, "topk_group": 1, "topk_method": "greedy", "torch_dtype": "bfloat16", "use_mla": false, "v_head_dim": 0, "vocab_size": 129280 }, "lm_head": true, "max_position_embeddings": 32768, "model_type": "deepseek_vl_v2", "moe_intermediate_size": 896, "moe_layer_freq": 1, "mtp_clone_unshared_weights": false, "mtp_mask_mode": "position", "mtp_moe": false, "mtp_num_heads": 1, "mtp_num_speculative_steps": 3, "mtp_recursive": true, "mtp_rmsnorm_init": "ones", "mtp_share_embedding_weights": true, "mtp_share_lm_head": true, "mtp_share_norm": true, "num_nextn_predict_layers": 1, "n_group": 1, "n_routed_experts": 64, "n_shared_experts": 2, "norm_topk_prob": false, "num_attention_heads": 10, "num_experts_per_tok": 6, "num_hidden_layers": 12, "num_key_value_heads": 10, "output_router_logits": false, "pad_token_id": 2, "pretraining_tp": 1, "projector_config": { "input_dim": 2048, "model_type": "mlp_projector", "n_embed": 1280, "projector_type": "linear" }, "q_lora_rank": null, "qk_nope_head_dim": 0, "qk_rope_head_dim": 0, "rm_head": false, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 1000000, "rope_type": "default" }, "rope_scaling": null, "rope_theta": 1000000, "routed_scaling_factor": 1.0, "scoring_func": "softmax", "tie_word_embeddings": false, "tile_tag": "2D", "topk_group": 1, "topk_method": "greedy", "transformers_version": "4.57.3", "use_cache": true, "use_mla": false, "v_head_dim": 0, "vary_num_decoder_layers": null, "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 } } }, "vocab_size": 129280 }