初始化项目,由ModelHub XC社区提供模型

Model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-14 12:53:37 +08:00
commit 7d6a7eafdf
29 changed files with 34813 additions and 0 deletions

1
tokenizer_config.json Normal file
View File

@@ -0,0 +1 @@
{"do_lower_case": true, "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer", "tokenizer_class": "PreTrainedTokenizerFast"}