es2 / tokenizer_config.json
huranokuma's picture
Training in progress, step 1000
3d33c21
raw
history blame
529 Bytes
{
"additional_special_tokens": [],
"bos_token": "<s>",
"cls_token": "[CLS]",
"do_lower_case": true,
"eos_token": "</s>",
"extra_ids": 0,
"mask_token": "[MASK]",
"name_or_path": "rinna/japanese-gpt2-medium",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--rinna--japanese-gpt2-medium/snapshots/f464b76739c884d8b0479a0a7705b7fa71c3fd5a/special_tokens_map.json",
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}