24 lines
583 B
JSON
24 lines
583 B
JSON
{
|
|
"add_prefix_space": false,
|
|
"backend": "tokenizers",
|
|
"bos_token": "<|endoftext|>",
|
|
"clean_up_tokenization_spaces": true,
|
|
"cls_token": "<|cls|>",
|
|
"eod_token": "<|endoftext|>",
|
|
"eos_token": "<|im_end|>",
|
|
"errors": "replace",
|
|
"is_local": true,
|
|
"local_files_only": true,
|
|
"mask_token": "<|mask|>",
|
|
"max_length": 7680,
|
|
"model_max_length": 32768,
|
|
"model_specific_special_tokens": {
|
|
"eod_token": "<|endoftext|>"
|
|
},
|
|
"pad_token": "<|pad|>",
|
|
"sep_token": "<|sep|>",
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"unk_token": "<|unk|>",
|
|
"vocab_size": 102400
|
|
}
|