初始化项目,由ModelHub XC社区提供模型

Model: Kalaoke/embeddings_dense_model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-29 23:54:33 +08:00
commit 5a52630e7d
17 changed files with 61416 additions and 0 deletions

1
tokenizer_config.json Normal file
View File

@@ -0,0 +1 @@
{"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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "training-msmarco-distilbert-base-v4-2022-03-14_09-06-48/", "tokenizer_class": "DistilBertTokenizer"}