14 lines
342 B
JSON
14 lines
342 B
JSON
|
{
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"additional_special_tokens": [
|
||
|
|
"<|endoftext|>"
|
||
|
|
],
|
||
|
|
"bos_token": "<|endoftext|>",
|
||
|
|
"clean_up_tokenization_spaces": true,
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"model_max_length": 1000000000000000019884624838656,
|
||
|
|
"tokenizer_class": "GPT2Tokenizer",
|
||
|
|
"unk_token": "<|endoftext|>",
|
||
|
|
"vocab_size": 49152
|
||
|
|
}
|