Skip to content
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.

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

Fix make_mlp_unpacked with lora #1209

Merged
merged 2 commits into from
Feb 3, 2025
Merged

Conversation

jambayk
Copy link
Contributor

@jambayk jambayk commented Jan 30, 2025

  • The check was done on the mlp module instead of the gate_up_linear module so it always returned False.
  • Need to access lora_B from gate_up_linear.
  • Code referred to k_proj and v_proj

apsonawane
apsonawane previously approved these changes Jan 30, 2025
@jambayk jambayk force-pushed the jambayk/mlp-unpacked-lora branch from ba0f867 to df12a59 Compare February 3, 2025 22:18
@kunal-vaishnavi kunal-vaishnavi enabled auto-merge (squash) February 3, 2025 22:19
@kunal-vaishnavi kunal-vaishnavi merged commit 61e8efb into main Feb 3, 2025
14 checks passed
@kunal-vaishnavi kunal-vaishnavi deleted the jambayk/mlp-unpacked-lora branch February 3, 2025 23:47
baijumeswani pushed a commit that referenced this pull request Feb 4, 2025
- The check was done on the `mlp` module instead of the `gate_up_linear`
module so it always returned False.
- Need to access lora_B from `gate_up_linear`. 
- Code referred to k_proj and v_proj
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants