Dakai "Steven" Men

Hi all, I just experienced a situation where LLaMA2 and Mistral generate a completion very slowly (sometimes even no response after around 1h) and seem not to be correct. I...

Calling the model in parallel

5

Hello, I'm currently using RelBERT for my experiment and it is quite slow when calling it. ```python pairlist = [['token1', 'token2'], ...] for pair in pairlist: emb = model.get_embedding(pair) #...

Continuously showing "Something Went Wrong" While Adding a Source

5

**Describe the bug** While attempting to add an IPTV m3u source, the frontend continuously reports "something went wrong". **To Reproduce** Steps to reproduce the behavior: 1. Access the frontend from...