Skip to content

feat(qwen3-next): Adds targeting of shared expert and attention modules #3183

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
NanoCode012 merged 2 commits into from
Sep 25, 2025
Merged

feat(qwen3-next): Adds targeting of shared expert and attention modules #3183

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
34f8854
Adds targetting of shared expert and attention modules in each layer
Sep 24, 2025
31362aa
Update VRAM usage
Sep 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion examples/qwen3-next/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ pip3 uninstall -y causal-conv1d && pip3 install flash-linear-attention==0.3.2
axolotl train examples/qwen3-next/qwen3-next-80b-a3b-qlora.yaml
```

This config uses about 41.7 GiB VRAM.
This config uses about 45.62 GiB VRAM.

Let us know how it goes. Happy finetuning! 🚀

Expand Down
8 changes: 8 additions & 0 deletions examples/qwen3-next/qwen3-next-80b-a3b-qlora.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,14 @@ lora_r: 16
lora_alpha: 8
lora_dropout: 0.05
lora_target_modules:
- linear_attn.in_proj_ba
- linear_attn.in_proj_qkvz
- linear_attn.out_proj
- shared_expert.up_proj
- shared_expert.down_proj
- shared_expert.gate_proj
- shared_expert_gate
- mlp.gate
Comment thread
NanoCode012 marked this conversation as resolved.
- q_proj
- v_proj
- k_proj
Expand Down