Bowen LIU comments

Repositories
Issues
Comments

Results 5 comments of


                                            Bowen LIU

How to load my local model

> > > @mrwyattii Thank you for your help. We have 8 24G GPUs, but it seems that I cannot specify which gpu to use by specifying CUDA_VISIBLE_DEVICES.谢谢你的帮助。我们有 8 个...

Qwen3-30B-A3B OOM with GRPO on 4x8H200 141G

same issue

ray.exceptions.ActorDiedError: The actor died unexpectedly before finishing this task.

same issue

Linux version install package has non-standard package name.

The same thing occurs. Just Do things Below: --- ### Steps to Fix the Issue #### 1. **Repackage the `.deb` File with a Valid Package Name** Manually extract the `.deb`...

Dialogue length decrease when training Qwen2.5-1.5B with 16bit LORA GRPO RL

The model seems to be doing great on format_reward and correctness_reward. Do you have an official training report that I can refer to? Also, I trained the model using the...