config.json

{
  "architectures": [
    "DeepseekOcr2ForConditionalGeneration"
  ],
  "dtype": "bfloat16",
  "image_token_id": 128815,
  "model_type": "deepseek_ocr2",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "dtype": "bfloat16",
    "eos_token_id": 1,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 1280,
    "initializer_range": 0.02,
    "intermediate_size": 6848,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "mlp_layer_types": [
      "dense",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse"
    ],
    "model_type": "deepseek_ocr2_text",
    "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,
    "pad_token_id": null,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "default"
    },
    "routed_scaling_factor": 1.0,
    "tie_word_embeddings": false,
    "topk_group": 1,
    "topk_method": "greedy",
    "use_cache": true,
    "vocab_size": 129280
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.10.0.dev0",
  "vision_config": {
    "dtype": "bfloat16",
    "encoder_config": {
      "_name_or_path": "",
      "architectures": null,
      "attention_dropout": 0.0,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "dtype": null,
      "eos_token_id": null,
      "hidden_act": "silu",
      "hidden_size": 896,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_range": 0.02,
      "intermediate_size": 4864,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "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"
      ],
      "max_position_embeddings": 32768,
      "max_window_layers": 28,
      "model_type": "deepseek_ocr2_encoder",
      "num_attention_heads": 14,
      "num_hidden_layers": 24,
      "num_key_value_heads": 2,
      "output_attentions": false,
      "output_hidden_states": false,
      "pad_token_id": null,
      "problem_type": null,
      "return_dict": true,
      "rms_norm_eps": 1e-06,
      "rope_parameters": {
        "rope_theta": 1000000.0,
        "rope_type": "default"
      },
      "sliding_window": null,
      "tie_word_embeddings": false,
      "use_cache": true,
      "use_sliding_window": false,
      "vocab_size": 1
    },
    "model_type": "deepseek_ocr2_vision",
    "sam_config": {
      "_name_or_path": "",
      "architectures": null,
      "attention_dropout": 0.0,
      "chunk_size_feed_forward": 0,
      "downsample_channels": [
        512,
        896
      ],
      "dtype": 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_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-06,
      "mlp_dim": 3072,
      "mlp_ratio": 4.0,
      "model_type": "deepseek_ocr2_sam_vision_model",
      "num_attention_heads": 12,
      "num_channels": 3,
      "num_hidden_layers": 12,
      "output_attentions": false,
      "output_channels": 256,
      "output_hidden_states": false,
      "patch_size": 16,
      "problem_type": null,
      "qkv_bias": true,
      "return_dict": true,
      "scale": 384,
      "use_abs_pos": true,
      "use_rel_pos": true,
      "window_size": 14
    }
  },
  "vocab_size": 500
}