{ "architectures": [ "DeepseekOcrForConditionalGeneration" ], "auto_map": { "AutoConfig": "modeling_deepseekocr.DeepseekOCRConfig", "AutoModel": "modeling_deepseekocr.DeepseekOCRForCausalLM" }, "bos_token_id": 0, "candidate_resolutions": [ [ 1024, 1024 ] ], "dtype": "bfloat16", "eos_token_id": 1, "first_k_dense_replace": 1, "global_view_pos": "head", "hidden_size": 1280, "image_grid_pinpoints": [ [ 1024, 1024 ] ], "image_token_id": 128815, "image_token_index": 128815, "intermediate_size": 6848, "kv_lora_rank": null, "lm_head": true, "max_position_embeddings": 8192, "model_type": "deepseek_ocr", "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, "projector_config": { "depth": 1, "dtype": "bfloat16", "input_dim": 2048, "model_type": "deepseek_ocr_projector", "n_embed": 1280, "projector_type": "linear" }, "q_lora_rank": null, "qk_nope_head_dim": 0, "qk_rope_head_dim": 0, "rm_head": false, "text_config": { "architectures": [ "DeepseekV2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_deepseekv2.DeepseekV2Config", "AutoModel": "modeling_deepseek.DeepseekV2Model", "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM" }, "bos_token_id": 0, "dtype": "bfloat16", "eos_token_id": 1, "first_k_dense_replace": 1, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1280, "initializer_range": 0.02, "intermediate_size": 6848, "kv_lora_rank": null, "lm_head": true, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "deepseek_v2", "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, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "routed_scaling_factor": 1.0, "topk_group": 1, "topk_method": "greedy", "use_cache": true, "use_mla": false, "v_head_dim": 0, "vocab_size": 129280 }, "tile_tag": "2D", "topk_group": 1, "topk_method": "greedy", "transformers_version": "5.0.0.dev0", "use_mla": false, "v_head_dim": 0, "vision_config": { "clip_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dtype": null, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "quick_gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 224, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "deepseek_ocr_clip_vision", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "projection_dim": 768, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "typical_p": 1.0 }, "dtype": "bfloat16", "image_size": 1024, "mlp_ratio": 3.7362, "model_name": "deeplip_b_l", "model_type": "deepseek_ocr_vision", "patch_size": 16, "sam_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "downsample_channels": [ 512, 1024 ], "dtype": null, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "global_attn_indexes": [ 2, 5, 8, 11 ], "hidden_act": "gelu", "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 1024, "initializer_range": 1e-10, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "mlp_dim": 3072, "mlp_ratio": 4.0, "model_type": "deepseek_ocr_sam_vision", "no_repeat_ngram_size": 0, "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 12, "num_return_sequences": 1, "out_channels": 256, "output_attentions": false, "output_channels": 256, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 16, "prefix": null, "problem_type": null, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "use_abs_pos": true, "use_rel_pos": true, "window_size": 14 }, "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 } } }, "vision_feature_layer": -1, "vision_feature_select_strategy": "default", "vocab_size": 129280 }