viet-gpt2 / tokenizer_config.json
vietdata's picture
Upload tokenizer
11a3811
raw
history blame
313 Bytes
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token_id": 50256,
"padding_side": "right",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}