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

aimV2: Are you planning on releasing the Causal Multimodal Decoder? #13

Open
msciancalepore98 opened this issue Nov 23, 2024 · 5 comments

Comments

@msciancalepore98
Copy link

Hey,

first thing first thanks for this piece of work, the cleanliness of the project is top notch.

However, I only see the definitions of, let's say, the encoder components of the network even though the title of your paper highlights "Multimodal Autoregressive Pre-training".

Are you planning on releasing both the decoders and training code of aimv2 ? That's the most interesting part of all this, which I hoped I would find in the repo :sadge

Thank you :)

@msciancalepore98 msciancalepore98 changed the title Are you planning on releasing the Causal Multimodal Decoder? aimV2: Are you planning on releasing the Causal Multimodal Decoder? Nov 23, 2024
@williamberrios
Copy link

+1

1 similar comment
@zijinY
Copy link

zijinY commented Nov 25, 2024

+1

@aelnouby
Copy link
Collaborator

Unfortunately, there are no plans currently to open-source the decoder weights.

@msciancalepore98
Copy link
Author

This was already clear, in fact the question was:

Are you planning on releasing both the decoders and training code of aimv2 ?

@dongdk
Copy link

dongdk commented Dec 16, 2024

+1

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants