materials.selfies-ted2m / tokenizer_config.json
matthewpwilson-ibm's picture
Initial commit
d9bfa88
raw
history blame contribute delete
445 Bytes
{
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "zinc22-16B-tokenizer",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/u/indra/.cache/huggingface/transformers/410b9713b9ff338491c4439bb9c3426a17c79e66c5a02f0a729b5455a334037a.7da70648c6cb9951e284c9685f9ba7ae083dd59ed1d6d84bdfc0584a4ea94b6d",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}