初始化项目,由ModelHub XC社区提供模型

Model: flax-sentence-embeddings/all_datasets_v3_mpnet-base
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-13 17:05:22 +08:00
commit db782f0d5a
14 changed files with 31707 additions and 0 deletions

1
tokenizer_config.json Normal file
View File

@@ -0,0 +1 @@
{"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "output/all_datasets_v3_mpnet-base/120000", "tokenizer_class": "MPNetTokenizer"}