tifilBERT-Base / tokenizer_config.json
suayptalha's picture
Add new SentenceTransformer model
784e390 verified
raw
history blame contribute delete
707 Bytes
{
"backend": "tokenizers",
"bos_token": "<bos>",
"clean_up_tokenization_spaces": false,
"cls_token": "<bos>",
"eos_token": "<eos>",
"extra_special_tokens": [
"<start_of_turn>",
"<end_of_turn>"
],
"is_local": true,
"mask_token": "<mask>",
"max_length": 128,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 128,
"pad_to_multiple_of": null,
"pad_token": "<pad>",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "<eos>",
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}