PaddleOCR-VL-hf / tokenizer_config.json
merve's picture
merve HF Staff
Upload processor
95c80fc verified
raw
history blame contribute delete
775 Bytes
{
"add_prefix_space": false,
"auto_map": {
"AutoProcessor": "processing_paddleocr_vl.PaddleOCRVLProcessor"
},
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": "<|begin_of_sentence|>",
"eos_token": "</s>",
"image_token": "<|IMAGE_PLACEHOLDER|>",
"is_local": true,
"legacy": true,
"mask_token": "<mask:1>",
"model_max_length": 131072,
"model_specific_special_tokens": {
"image_token": "<|IMAGE_PLACEHOLDER|>"
},
"pad_token": "<unk>",
"processor_class": "PaddleOCRVLProcessor",
"sep_token": "<|end_of_sentence|>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>",
"use_default_system_prompt": false
}