Ejafa

Any idea on how to reproduce vicuna in Nvidia L4?

1

Hi,, I have been trying to reproduce vicuna in 4xL4 which is 4*24=96 gb vram. What approach should I follow? Train.py oom error Train_mem.py oom error Left is Lora but...

[Bug Report] pusher-v4 in the environment doesn't collide the object for the fork

1

Please check: pusher.xml if there's any problem ``` ```

Support Fine-tune on PeFT adaptation

1

This project is great and the dataset is unique. To provide help to the community, it will be a great idea to support PeFT training on this dataset. Also, there's...

Recently, MOSS released the dataset of SFT [data](https://github.com/OpenLMLab/MOSS/tree/main/SFT_data) This project's dataset is quite related to The tool-former dataset. Is there any idea of adding a dataset where agents will have...