IcyTide

There should be 'return_sparse_embedding' in BGEM3FlagModel class

1

return_sparse_embedding arg exists in BGEM3ForInference, but cannot pass this arg from BGEM3FlagModel

Provide a normalized algorithm for compute lexical similar score

1

Same sentences can always get a "1" simirlar score like dense way but not a score less than 1 and change with different sentence content. Different sentences can get an...

About the prompt template

2

Hi, I want to know that you fine-tune the llama2 model with totally different prompt template from Meta as below: To get the expected features and performance for the chat...

JCL中出现 造成伤害-Buff添加 的子序列，实际表现却为先造成的伤害吃到了后刷新的BUFF，能否增加刷新频率保持精度？ 可以考虑删除类型19， 20：技能施放日志，技能施放结果日志。这两者占据了50%-80%的日志内容，且对分析帮助不大