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.

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

Jump to bottom

generate silently fails on OpenELM 3B after latest commit #69

Closed
DePasqualeOrg opened this issue May 9, 2024 · 4 comments
Closed

generate silently fails on OpenELM 3B after latest commit #69

DePasqualeOrg opened this issue May 9, 2024 · 4 comments

Comments

@DePasqualeOrg
Copy link
Contributor

DePasqualeOrg commented May 9, 2024 •
edited

[Original comment removed, see below]

import Foundation
import MLXLLM

extension ModelConfiguration {
  static let openelm3b = ModelConfiguration(
    id: "mlx-community/OpenELM-3B"
  ) { prompt in
    "\(prompt)"
  }
}
@DePasqualeOrg
Copy link
Contributor Author

DePasqualeOrg commented May 9, 2024 •
edited

[Original comment removed, see below]

@DePasqualeOrg
Copy link
Contributor Author

The silent failing of OpenELM 3B seems to be caused by commit ff7610d. It doesn't happen when checking out the commit before that.

@DePasqualeOrg DePasqualeOrg changed the title Extending ModelConfiguration when importing MLXLLM generate silently fails on OpenELM 3B as of latest commit May 9, 2024
@DePasqualeOrg DePasqualeOrg changed the title generate silently fails on OpenELM 3B as of latest commit generate silently fails on OpenELM 3B after latest commit May 9, 2024
@davidkoski
Copy link
Collaborator

OK, #53 should address this

davidkoski added a commit that referenced this issue May 20, 2024
@davidkoski
handle partially quantized models
0b5cb5f 
- fix for #53 #71 #69 #74
- in order to test the models
	- I added a default prompt of an appropriate form
	- while working on the model configuration also added additional stop tokens (#74)
- fixed the repetitionPenalty code (#71)
@davidkoski davidkoski mentioned this issue May 20, 2024
Merged
davidkoski added a commit that referenced this issue May 28, 2024
@davidkoski
handle partially quantized models (#76)
9d74afd 
* handle partially quantized models

- fix for #53 #71 #69 #74
- in order to test the models
	- I added a default prompt of an appropriate form
	- while working on the model configuration also added additional stop tokens (#74)
- fixed the repetitionPenalty code (#71)
@davidkoski
Copy link
Collaborator

#76 should fix this

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@DePasqualeOrg @davidkoski