mrbert-berria-ft / tokenizer_config.json
cuadron11's picture
Add new SentenceTransformer model
6a4e3b5 verified
{
"add_prefix_space": true,
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"extra_special_tokens": [
"<mask>"
],
"is_local": false,
"legacy": true,
"mask_token": "<mask>",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 8192,
"pad_token": "<pad>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>",
"use_default_system_prompt": false
}