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

Add Instructions for Loading Llama2 Models #1051

Closed
Quentin-Anthony opened this issue Sep 29, 2023 · 5 comments · Fixed by #1124
Closed

Add Instructions for Loading Llama2 Models #1051

Quentin-Anthony opened this issue Sep 29, 2023 · 5 comments · Fixed by #1124
Assignees
@Quentin-Anthony @IshanMi
Labels
feature request New feature or request

Comments

@Quentin-Anthony
Copy link
Member

We need to test that the Llama2 instructions from EleutherAI/math-lm#53 work in upstream, then add documentation on it.
@Quentin-Anthony Quentin-Anthony added the feature request New feature or request label Sep 29, 2023
@StellaAthena
Copy link
Member

It would be strongly desirable to prioritize this, as we would like it to be upstreamed in time for the LLeMA release (currently looks like this will be happening next week)

@Quentin-Anthony
Copy link
Member Author

It would be strongly desirable to prioritize this, as we would like it to be upstreamed in time for the LLeMA release (currently looks like this will be happening next week)

Will do

@StellaAthena StellaAthena mentioned this issue Oct 12, 2023
Open
@IshanMi
Copy link

IshanMi commented Dec 24, 2023

Is anyone working on this, or could I take it up?

@StellaAthena
Copy link
Member

Is anyone working on this, or could I take it up?

You're welcome to take it on.

@haileyschoelkopf
Copy link
Contributor

@IshanMi you may want to take a look at #1050 and @AIproj ’s fork which is in the process of adding mistral support (and is very close to being merge-ready) as help on this—it adds the GQA support from the Llemma fork, as well as Meta format Llama2 -> NeoX conversion, which should be helpful!

@haileyschoelkopf haileyschoelkopf linked a pull request Jan 17, 2024 that will close this issue
Improve Conversion Utilities #1124
Merged
9 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Quentin-Anthony Quentin-Anthony

@IshanMi IshanMi

Labels
feature request New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Improve Conversion Utilities EleutherAI/gpt-neox
5 participants
@Quentin-Anthony @StellaAthena @kshitijkg @IshanMi @haileyschoelkopf