text_extraction / tokenizer_config.json
phonsobon's picture
Add Surya OCR model
310ad98 verified
{
"added_tokens_decoder": {
"66553": {
"content": "</S>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"66556": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "</S>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<PAD>",
"processor_class": "MultimodalFoundationProcessor",
"tokenizer_class": "GreedyMathUTF16Tokenizer",
"unk_token": null
}