Last active
September 21, 2025 10:50
-
-
Save qunash/820c86d1d267ec8051d9f68b4f4bb656 to your computer and use it in GitHub Desktop.
grpo_qwen-0-5b_single_t4.ipynb
use_vllm=False
fixes the above. Does the config strictly require >1 GPU? If so how did your initial notebook config work on a colab t4 instance?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
The train function gives an error:
TypeError: EngineArgs.__init__() got an unexpected keyword argument 'device'.