jinaai
/

jina-embeddings-v2-base-zh

Feature Extraction

sentence-transformers

Transformers.js

sentence-similarity

text-embeddings-inference

Model card Files Files and versions Community

Resources

View closed (9)

Fast and slow tokenizers mismatch due to custom normalization

#16 opened about 2 months ago by

JinaBertModel is not compatible with output_attentions=True

#15 opened 2 months ago by

下载权重后从本地读取会报错，`BertModel`没有`encode`方法。但是使用from_pretrained从hf下载的文件却可以正常使用

#14 opened 3 months ago by

使用一台有8G内存的服务器，按示例加载模型，出现OOM错误

#11 opened 6 months ago by

I would like to ask why the results obtained by calling the method according to the model you gave are different every time?

#8 opened 8 months ago by

jinaai/jina-bert-implementation is not the path to a directory containing a file named configuration_bert.py.

#7 opened 10 months ago by

How to use onnx model ? I need to accerlate the embedding

#6 opened 10 months ago by