gpt2_1000t_1M_256d_8l / tokenizer_config.json
jumelet's picture
Training in progress, step 1757
fe516a9
raw
history blame contribute delete
334 Bytes
{
"additional_special_tokens": [
"<unk>",
"<pad>",
"<mask>",
"<bos>"
],
"bos_token": "<bos>",
"clean_up_tokenization_spaces": true,
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}