DARv2 / tokenizer_config.json
nikodallanoce's picture
Add new SentenceTransformer model
8ddf12d verified
Raw History Blame Contribute Delete
596 Bytes
{
"backend": "tokenizers",
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|end_of_text|>",
"is_local": false,
"local_files_only": false,
"mask_token": "<|mask|>",
"max_length": 2048,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 2048,
"pad_to_multiple_of": null,
"pad_token": "<|pad|>",
"pad_token_type_id": 0,
"padding_side": "right",
"stride": 0,
"tokenizer_class": "TokenizersBackend",
"truncation": true,
"truncation_side": "right",
"truncation_strategy": "longest_first"
}