config.json

{
    "_attn_implementation_autoset": false,
    "add_cross_attention": false,
    "architectures": [
        "DeepseekOCRForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "modeling_deepseekocr.DeepseekOCRConfig",
        "AutoModel": "modeling_deepseekocr.DeepseekOCRForCausalLM"
    },
    "aux_loss_alpha": 0.001,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "candidate_resolutions": [
        [
            1024,
            1024
        ]
    ],
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 1,
    "ep_size": 1,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "first_k_dense_replace": 1,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "global_view_pos": "head",
    "hidden_act": "silu",
    "hidden_size": 1280,
    "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 6848,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "kv_lora_rank": null,
    "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
    },
    "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
    },
    "length_penalty": 1.0,
    "lm_head": true,
    "max_length": 20,
    "max_position_embeddings": 8192,
    "min_length": 0,
    "model_type": "DeepseekOCR",
    "moe_intermediate_size": 896,
    "moe_layer_freq": 1,
    "n_group": 1,
    "n_routed_experts": 64,
    "n_shared_experts": 2,
    "no_repeat_ngram_size": 0,
    "norm_topk_prob": false,
    "num_attention_heads": 10,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_experts_per_tok": 6,
    "num_hidden_layers": 12,
    "num_key_value_heads": 10,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "pretraining_tp": 1,
    "problem_type": null,
    "projector_config": {
        "input_dim": 2048,
        "model_type": "mlp_projector",
        "n_embed": 1280,
        "projector_type": "linear"
    },
    "pruned_heads": {},
    "q_lora_rank": null,
    "qk_nope_head_dim": 0,
    "qk_rope_head_dim": 0,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rm_head": false,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "routed_scaling_factor": 1.0,
    "scoring_func": "softmax",
    "sep_token_id": null,
    "seq_aux": true,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tile_tag": "2D",
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "topk_group": 1,
    "topk_method": "greedy",
    "torchscript": false,
    "transformers_version": "4.47.1",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "use_mla": false,
    "v_head_dim": 0,
    "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
}