sigjhl
sigjhl
@user074 Hey can you make a branch with your classification-enabled code? I'm doing lots of classification but HF trainer eats up so much VRAM :( I'd love to try it...
@kddubey @user074 Thank you for the tips! On my dataset, qlora on e5-mistral (with classification head) did better than a fully finetuned BERT variant (ALBERT-xxl) and surprisingly, better than a...
> Hello everyone, > > Recently I noticed a lack of 4-bit quantized versions of `Google/flan-ul2` on HF, and so, decided to set out to quantize the model on my...