Sam Comber

+1 on this, I'm having to use 0.4.0 else DEPLOYING stuck in loop with 0.5.0 @JGSweets (thanks for your comment, got me up and running)

Hi @slumnitz, unfortunately I'm quite tied up finishing off my PhD and internship (concurrently) at the moment, so my time is quite limited for the next two months or so....

`await self.stream.input_stream.end_stream()` seemed to fix this for me if anyone else is having issue!

@tportenier Would it be possible to share the modification? I'm interested in doing similar.

I am seeing this too when testing a qlora adapter tuned from a quantized model! ``` config = LoraConfig( r=8, lora_alpha=16, target_modules=[ "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj", "lm_head",...