初始化项目,由ModelHub XC社区提供模型

Model: vocab-transformers/dense_encoder-msmarco-distilbert-word2vec256k
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-30 21:42:27 +08:00
commit 5b8d70df1c
12 changed files with 256621 additions and 0 deletions

1
tokenizer_config.json Executable file
View File

@@ -0,0 +1 @@
{"model_max_length": 512, "unk_token": "[UNK]", "cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]", "model_input_names": ["input_ids", "attention_mask"], "special_tokens_map_file": "/root/.cache/huggingface/transformers/fe09c361189d8238b9e387f10a088e93f70620bfe74b82036baff1fed512a153.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "nicoladecao/msmarco-word2vec256000-distilbert-base-uncased", "tokenizer_class": "PreTrainedTokenizerFast"}