-
Notifications
You must be signed in to change notification settings - Fork 47
Phi 3.5 Vision Instruct Fails to Load "Trust remote code" error #29
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
Comments
Right now, by default we disable trusting remote code. We will need to update the LM Studio app UI so that users can configure their trust settings. Will update this issue when we are ready to ship this feature. |
Teuken 7B has the same problem. It also needs to trust remote code. Would love to see this feature in the future, too. |
mlx-community/Molmo-7B-D-0924-4bit has the same problem, |
Florence-2-large-ft-bf16 also |
@neilmehta24 what is the schedule to roll it out? We're facing the same with |
any updates ? thanks QQ |
up |
how to do this without UI ? |
up |
2 similar comments
up |
up |
having the same problem with phi 3.5, any updates? |
Has there been any updates on this? If not, what is the workaround for LM studio to allow loading og the models? |
same here, I'm having issues loading Florence and I can't figure out where to put the parameter to load the model using the UI. |
any progress? |
@neilmehta24 Any update on this, facing same issue |
I have a plan for the remote code issue so we can move forward. Unfortunately phi3.5 vision doesn't work out-of-the-gate in mlx-engine, likely due to a bug in mlx-engine. This will require more time for me to investigate. I have a draft PR up with a failing test #138 . I will see if I can carve out time to debug this test. For models that require this permission, the plan is add the "remote code" into the mlx-engine code base so that we can keep that permission off. The first goalpost is Phi 3.5 vision support |
mlx-community/Phi-3.5-vision-instruct-4bit fails to load in the current MLX build of LM Studio.
LM Studio version: 0.3.5(Build 4)
Sonoma 14.3/128gb M3 Max.
The text was updated successfully, but these errors were encountered: