JP Lorandi

Results 2 issues of JP Lorandi

I'm running the HF model `curiousily/falcon-7b-qlora-chat-support-bot-faq` on top of `tiiuae/falcon-7b` and it runs quite fast, but unfortunately there's no way to load it in lmql. I created the PeftModel class,...

enhancement

I implemented a PeftLLM backend (which I pasted into #152 ) but I cannot load it since there's no way to insert it into the registry via serve-model. I think...

enhancement