Hacker News new | ask | show | jobs
by zhisbug 1166 days ago
And I think the problem of taking the roles of users in vicuna is caused by this bug: https://github.com/lm-sys/FastChat/commit/1bb234265d16bdfd50...

which has been fixed recently.

Lmsys are launching new training jobs after this patch, please stay tuned.

1 comments

Nah, I don't use huggingface transformers to run inference with the vicuna model. I use llama.cpp. But I do appreciate the tip.

edit: Oh, I was completely wrong. That's in the training not the inference so it applies to all the weights.