17 lines
435 B
JSON
17 lines
435 B
JSON
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"additional_special_tokens": null,
|
||
|
|
"backend": "tokenizers",
|
||
|
|
"bos_token": "<|endoftext|>",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"errors": "replace",
|
||
|
|
"is_local": false,
|
||
|
|
"model_max_length": 65536,
|
||
|
|
"model_specific_special_tokens": {},
|
||
|
|
"pad_token": "<|pad|>",
|
||
|
|
"tokenizer_class": "GPT2Tokenizer",
|
||
|
|
"unk_token": "<|endoftext|>"
|
||
|
|
}
|