Shan Chen

请问为什么只做了5个标签的预测，全部数据9标签结果怎么样呢？

1

多谢！祝万事如意

may i ask what is the version for transformers and peft?

3

miniconda3/envs/lora/lib/python3.9/site-packages/peft/tuners/lora.py", line 154, in _find_and_replace "memory_efficient_backward": target.state.memory_efficient_backward, AttributeError: 'MatmulLtState' object has no attribute 'memory_efficient_backward'

Hi! Thanks for the cool videos as always! I just use their example algo on their github and ran on your dataset, the result is actually worse...

MeZO on continue pre-training

1

Hi! Really nice work! I am wondering whether any have tried MeZO on continue pertaining LLM. If so, I am wondering the performance and insights are, thanks! Shan

Hi, I am wondering whether this support training for second gen Gemma based llava. When we trained with the new Gemma with this repo, we ran into an error of:...