azahead-longformer-v1.0 / tokenizer_config.json
zwellington's picture
Training in progress, step 20
0dca7b3
raw
history blame
355 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 4096,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "LongformerTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}