2023MLMA_LAB9_task2 / tokenizer_config.json
yujie07's picture
Training in progress, epoch 1
d3d0550
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"model_max_length": 1024,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "BioGptTokenizer",
"unk_token": "<unk>"
}