lm_training / tokenizer_config.json
jumelet's picture
End of training
d14fe41
raw
history blame
199 Bytes
{
"bos_token": "<s>",
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}