KJW

When using the oasst1 (OpenAssistant) dataset, I noticed that the 'input' in the dataset gets stripped away in [`format_dataset` function](https://github.com/artidoro/qlora/blob/bdc655dfa71e5ef1553a078980fb5083c346a4cf/qlora.py#L550), and that both the instruction and answer are contained in...

Error serving baize-lora-7B

1

I'm trying to host my arena, but I want to do so with models that have been finetuned using QLoRA. To test if LoRA models worked, I thought I'd first...

Diverging evaluation loss using finetuning scripts Guanaco 7b

8

Is anyone else having this issue when using the [finetune_guanaco_7b.sh](https://github.com/artidoro/qlora/blob/main/scripts/finetune_guanaco_7b.sh) script? I keep seeing the evaluation loss diverge rather than converge. I noticed this originally trying to finetune on my...