Skip to content

Add DSpark support for Qwen/Qwen3.6-27B - #75

Open
James-Bao wants to merge 2 commits into
deepseek-ai:mainfrom
James-Bao:add-dspark-qwen36-27b
Open

Add DSpark support for Qwen/Qwen3.6-27B#75
James-Bao wants to merge 2 commits into
deepseek-ai:mainfrom
James-Bao:add-dspark-qwen36-27b

Conversation

@James-Bao

Copy link
Copy Markdown

Add training config and model constant for the Qwen3.6-27B model. The model has 64 hidden layers; target_layer_ids are evenly spaced with stride 15 across the full depth.

James Bao added 2 commits July 29, 2026 00:53
Add training config and model constant for the Qwen3.6-27B model.
The model has 64 hidden layers; target_layer_ids are evenly spaced
with stride 15 across the full depth.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant