-
Notifications
You must be signed in to change notification settings - Fork 403
Add gpt_oss model #354
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
Add gpt_oss model #354
Conversation
Co-authored-by: Neil Mehta <neil@lmstudio.ai> Co-authored-by: Matt Clayton <matt@lmstudio.ai>
| x = x * mx.expand_dims(expert_weights, axis=2) | ||
| return x.sum(axis=1) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sometimes it's important to do the sum in fp32.. maybe check another implementation to see?
|
@awni Is fine-tuning included in this update? |
|
|
|
@niryuu where are you getting this error? |
|
Presumably from trying to load the original model in mlx-lm (which is expected to not work). You can reproduce it with e.g. |
|
Ok you should be able to load the original models now. I added a dequant step if needed: And: On an M2 Ultra: |
|
Yep, it works! Uploading quants now. Are we good to merge? |
|
Yep. LGTM |
awni
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great work @christian-lms and the rest of the LM Studio team!!
|
@awni Would it be possible to support fine-tuning? |
Contribution by LM Studio Team. Initial implementation, more details to follow. Please note numerical precision considerations vs. the reference implementation.