roberta-ar / tokenizer_config.json
gagan3012's picture
Upload tokenizer
77df2e0
{
"add_prefix_space": false,
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 512,
"name_or_path": "/lustre07/scratch/gagan30/arocr/models/roberta-ar",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": null,
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}