danishboy000
danishboy000
I tried this and the quality didn't match.
> This thread is related: [huggingface/peft#1639](https://github.com/huggingface/peft/issues/1639). Cc: @BenjaminBossan Thanks @sayakpaul just to be clear, my issue is related to CPU memory (RAM) and not GPU memory .
@BenjaminBossan the other thread is related to GPU memory while I'm facing this issue in CPU memory (RAM)
Yes, I am aware that adding load_lora_weights increases GPU memory, and that is working well for me. However, I have also observed an increase in CPU memory in production, which...
> Thanks for providing more details. Just to be completely clear, so that I can attempt to replicate: > > 1. The model is on GPU but you observe a...
Here I've run your exact same code, but for 500 iterations 