| { | |
| "library_name": "zeromodels", | |
| "preprocessor_module": "zeromodels.sentence_transformers", | |
| "preprocessor_class": "ZMSentenceTransformerTokenizer", | |
| "variant": "all-MiniLM-L12-v2", | |
| "tokenizer_file": "tokenizer.json", | |
| "backbone_type": "bert", | |
| "tokenizer_config": { | |
| "do_lower_case": true, | |
| "unk_token": "[UNK]", | |
| "sep_token": "[SEP]", | |
| "pad_token": "[PAD]", | |
| "cls_token": "[CLS]", | |
| "mask_token": "[MASK]", | |
| "tokenize_chinese_chars": true, | |
| "strip_accents": null, | |
| "do_basic_tokenize": true, | |
| "never_split": null, | |
| "tokenizer_class": "BertTokenizer", | |
| "model_max_length": 512 | |
| }, | |
| "sentence_transformer_config": { | |
| "max_seq_length": 128, | |
| "do_lower_case": false | |
| } | |
| } | |