Skip to content

Conversation

allenwang28
Copy link
Contributor

Add Qwen 3 8B for larger scale testing compared to 1.7B

Also resolves #190

@meta-cla meta-cla bot added the CLA Signed This label is managed by the Meta Open Source bot. label Sep 22, 2025
@allenwang28 allenwang28 merged commit d5ae6c7 into meta-pytorch:main Sep 23, 2025
5 checks passed
@allenwang28 allenwang28 deleted the qwen3_8b branch September 23, 2025 14:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Meta Open Source bot.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

In torchtitan's trainer, _qwen3_hf_to_vllm num_layers is hardcoded to 28

2 participants