anlp-assignment2-models / tokenizer /tokenizer_config.json
anuml's picture
upload: tokenizer/tokenizer_config.json
95b640a verified
Raw History Blame Contribute Delete
322 Bytes
{
"backend": "tokenizers",
"bos_token": "<|bos|>",
"eos_token": "<|eos|>",
"extra_special_tokens": [
"<|trans|>",
"<|vi|>",
"<|ja|>",
"<|en|>"
],
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<|unk|>"
}