Download weights/ocr/tokenizer_config.json from spark-ux/indic-doc-parser: direct link, hf CLI and curl.
- Browser
- Download file 1.08 kB
-
https://huggingface.co/spark-ux/indic-doc-parser/resolve/main/weights/ocr/tokenizer_config.json
- Command line
-
hf download hf://spark-ux/indic-doc-parser/weights/ocr/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/spark-ux/indic-doc-parser/resolve/main/weights/ocr/tokenizer_config.json
1.08 kB
| { | |
| "backend": "tokenizers", | |
| "boi_token": "<|start_of_image|>", | |
| "bos_token": "[@BOS@]", | |
| "clean_up_tokenization_spaces": false, | |
| "eoi_token": "<|end_of_image|>", | |
| "eos_token": "<|im_end|>", | |
| "extra_special_tokens": [ | |
| "<|endoftext|>", | |
| "<|im_start|>", | |
| "<|im_end|>", | |
| "<|object_ref_start|>", | |
| "<|object_ref_end|>", | |
| "<|box_start|>", | |
| "<|box_end|>", | |
| "<|quad_start|>", | |
| "<|quad_end|>", | |
| "<|vision_start|>", | |
| "<|vision_end|>", | |
| "<|image_pad|>", | |
| "<|video_pad|>" | |
| ], | |
| "image_token": "<|image_pad|>", | |
| "is_local": true, | |
| "local_files_only": true, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "model_specific_special_tokens": { | |
| "boi_token": "<|start_of_image|>", | |
| "eoi_token": "<|end_of_image|>", | |
| "image_token": "<|image_pad|>" | |
| }, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "right", | |
| "processor_class": "Qwen3VLProcessor", | |
| "sp_model_kwargs": null, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |