amdnsr

Results 6 comments of amdnsr

QLoRA Training does not give expected results

@karths8 did you manage to resolve the above issue?

Error while trying to run training in Windows

I'm trying this on Tesla V100S, which has compute [capability 7.0](https://en.wikipedia.org/wiki/Nvidia_Tesla#:~:text=V100%20GPU%20accelerator%20), which satisfies the requirements for training. Also, I am able to do the training on the same GPU on...

OverflowError: out of range integral type conversion attempted while running python qlora.py

Running on Tesla V100 32GB GPU

V100 can not supprt load_in_4bit and fp16?

same issue for me

Trained model output seems illegible

@KKcorps were you able to find the issue and get any meaningful output from the trained models?

AttributeError: 'tuple' object has no attribute 'load_in_8bit' while trying inference

any suggestions why I'm facing this issue?