Fada_ar_embedding / tokenizer_config.json
masterofaudio2077's picture
FADA: ARBERTv2 contrastive fine-tune + distillation from Qwen/Qwen3-Embedding-8B
7c0556b verified
Raw History Blame Contribute Delete
593 Bytes
{
"backend": "tokenizers",
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"is_local": true,
"local_files_only": false,
"mask_token": "[MASK]",
"max_length": 200,
"model_max_length": 200,
"never_split": null,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}