Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

[RFC] Support DistillT5#652

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Draft
idostyle wants to merge3 commits intoleejet:master
base:master
Choose a base branch
Loading
fromidostyle:dt
Draft

Conversation

@idostyle
Copy link
Contributor

@idostyleidostyle commentedApr 9, 2025
edited
Loading

Add support forhttps://huggingface.co/LifuWang/DistillT5https://github.com/LifuWang-66/DistillT5

Can be tested withhttps://huggingface.co/Eviation/DistillT5 e.g.https://huggingface.co/Eviation/DistillT5/blob/main/DistillT5-F32.safetensors which removes the additional wrapping.

  • Probably needs to be integrated, and at best automatically detected, alongside T5 XXL
  • Check if there is a way to use the unmodified LifuWang DistillT5 model with the additional encoder wrapping on the tensor names
    image

I would appreciate any ideas on how best to incorporate this in a less intrusive way.

Green-Sky, fszontagh, stduhpf, rmatif, and vmobilis reacted with thumbs up emojiGreen-Sky, stduhpf, and JohnClaw reacted with rocket emoji
@stduhpf
Copy link
Contributor

Nice, just as I was thinking of adding it.

JohnClaw reacted with thumbs up emoji

Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@idostyle@stduhpf

[8]ページ先頭

©2009-2025 Movatter.jp