CodeBERT_Tokenizer_New / tokenizer_config.json
Meohong's picture
Upload tokenizer
dbf4a9e
raw
history blame
No virus
666 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "microsoft/codebert-base",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--microsoft--codebert-base/snapshots/3b0952feddeffad0063f274080e3c23d75e7eb39/special_tokens_map.json",
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}