Gabriele Venturi
Gabriele Venturi
@amrrs thanks a lot for reporting. I suspect it has to deal with the token limit. Unfortunately such models allow very low maximum of tokens. I'll try to investigate a...
Ok there seems to be a limit in the tokens amount. We are working on possible workaround to overcome these issues and integrate more LLM apart from OpenAI! I'll keep...
Update: I've been working on addressing this issue, and fix some of the problems related to make OpenAssistant work. However, it seems it's not "smart enough" to understand the complex...
Closing, as there are now open source LLMs performing better than open assistant and open assistant doesn't perform well enough
@amrrs I would just recommend using the OpenAI api or if you want a free one, I would suggest either Falcon or Starcoder!
Hey @johnson-52197, definitely a super nice-to-have feature, would love to have it integrated. I've assigned it to you! P.s. we are launching the discord server, in particular for the contributors,...
@Lorenzobattistela just assigned to you! Welcome onboard!
Here it is: https://discord.gg/AZRDpK4vt9 @Lorenzobattistela
Hey @PavelAgurov thanks a lot for reporting! Which LLM did you use? Can you try to run with `verbose=True` and share the log?
Well done @yzaparto great job!