weights/ocr/config.json

{
  "architectures": [
    "Qwen3_5ForConditionalGeneration"
  ],
  "chunk_size_feed_forward": 0,
  "dtype": "bfloat16",
  "eos_token_id": 262146,
  "generation_config": {
    "_from_model_config": true,
    "eos_token_id": 262146,
    "transformers_version": "5.6.2",
    "use_cache": true
  },
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "image_token_id": 262155,
  "is_encoder_decoder": false,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "model_type": "indic_ocr",
  "output_attentions": false,
  "output_hidden_states": false,
  "problem_type": null,
  "return_dict": true,
  "text_config": {
    "_name_or_path": "",
    "architectures": null,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_output_gate": true,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "dtype": "bfloat16",
    "eos_token_id": 262146,
    "full_attention_interval": 4,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 3584,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_types": [
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention"
    ],
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 16,
    "linear_value_head_dim": 128,
    "mamba_ssm_dtype": "float32",
    "max_position_embeddings": 262144,
    "mlp_only_layers": [],
    "model_type": "qwen3_5_text",
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "num_attention_heads": 8,
    "num_hidden_layers": 24,
    "num_key_value_heads": 2,
    "output_attentions": false,
    "output_hidden_states": false,
    "pad_token_id": 262144,
    "partial_rotary_factor": 0.25,
    "problem_type": null,
    "return_dict": true,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "mrope_interleaved": true,
      "mrope_section": [
        11,
        11,
        10
      ],
      "partial_rotary_factor": 0.25,
      "rope_theta": 10000000,
      "rope_type": "default"
    },
    "tie_word_embeddings": true,
    "use_cache": false,
    "vocab_size": 262157
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.6.2",
  "use_cache": false,
  "video_token_id": 262156,
  "vision_config": {
    "_name_or_path": "",
    "architectures": null,
    "chunk_size_feed_forward": 0,
    "deepstack_visual_indexes": [],
    "depth": 12,
    "dtype": "bfloat16",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "model_type": "qwen3_5_vision",
    "num_heads": 12,
    "num_position_embeddings": 2304,
    "out_hidden_size": 1024,
    "output_attentions": false,
    "output_hidden_states": false,
    "patch_size": 16,
    "problem_type": null,
    "return_dict": true,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_end_token_id": 262154,
  "vision_start_token_id": 262153
}