Alexandre Strube

@Hangzhi hey, we are waiting :-)

I am not sure this is a bug. The conversation keeps growing, until it fills up memory. On the web UI or on other frontends (like continue.dev), you see this...

Perhaps one could do a notebook with a less restrictive model, say, Mistral?

That depends on the model, really. I have models which do one or the other, with the exact same prompt. @suquark any news?

@suquark this is also related to #88, right?

I see what @yantao0527 describes with Marcoroni-70B, but not with WizardCoder-15 nor Mistral-7b-instruct. Interesting.

@Abhijit-2592 this is not an issue, really. As the chat gets longer, it takes more memory, which is freed when you clean the conversation, no?

Same for supercomputing environments where things run on bare metal.

@nd7141 @WGB0304 do you still see the issue? It looks like a sagemaker issue, not a fastchat one. Maybe we could close this?

@Ejafa that looks like lack of hardware, not much one can do here. Mind if we close this one?