BioLingual / tokenizer_config.json
davidrrobinson's picture
Upload processor
fc9e9d9
raw
history blame
414 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "<pad>",
"processor_class": "ClapProcessor",
"sep_token": "</s>",
"special_tokens_map_file": null,
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"trust_remote_code": false,
"unk_token": "<unk>"
}