shahajbert_nwp_finetuning_test4 / tokenizer_config.json
amirhamza11's picture
Training in progress, epoch 1
df52952
raw
history blame contribute delete
429 Bytes
{
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"eos_token": "[SEP]",
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}