FlagEmbedding issues

Multilingual Models

11

Do you plan to train and release multilingual embedding models in the near future?

Siegi96

提一个创新性的点，向量模型如何识别大小关系？

2

query：请帮我找出大于0.5的数据知识库：0.1，0.2，0.3，0.8，0.6 召回结果：0.6，0.8 向量模型能做到这种程度吗？

mechigonft

文本向量的存储和读取

1

长文本向量化后需要存储，节省之后每次计算的时间，请问官方有没有像gensim的save()那样保存词向量的方法呢

rabum

Loss function for fine-tuning

2

Hi, what is the name of the loss function used for fine-tuning? And could you please point me to where it is defined? Edit: looks like CrossEntropyLoss with In-Batch Negative...

austinmw

compute_lexical_matching_score VS ElasticSearch

1

如果我有一个ES，那么还需使用这个函数要计算这一项吗？ compute_lexical_matching_score

trillionmonster

Support vLLM for beacon models

1

https://github.com/vllm-project/vllm/issues/2676

pseudotensor

activation beacon Needle In A Haystack test failed

6

只有最后4k插入needle可以通过，前面插入全部失败。测试输入长度16k,32k,128k. [Needle In A Haystack](https://github.com/gkamradt/LLMTest_NeedleInAHaystack) 下面是29.5k长度测试输出 `******************** Input Length: 29605 Position: 0k Prediction: There are many great things to do in San Francisco! Here are some suggestions: 1. Visit...

gradetwo