Skip to content

Link North Small Translate W4A16 weights - #811

Merged
emanic-cohere merged 1 commit into
mainfrom
port/pr-75
Sep 10, 2026
Merged

Link North Small Translate W4A16 weights#811
emanic-cohere merged 1 commit into
mainfrom
port/pr-75

Conversation

@sync-github-public-private-repos

@sync-github-public-private-repos sync-github-public-private-repos Bot commented Sep 10, 2026

Copy link
Copy Markdown
Contributor

Ported from internal PR #75.

Original description:

Summary

  • replace the FP8 Hugging Face link on the North Small Translate page with the NVFP4 W4A16 model
  • update the surrounding copy to identify the linked quantization accurately

Validation

  • pnpm lint:markdown
  • pnpm docs:check

Linear: TW-974


Note

Low Risk
Documentation-only wording and link updates on a single model page; no runtime or API behavior changes.

Overview
Updates the North Small Translate model doc so open-weights guidance points at the NVFP4 W4A16 artifact instead of FP8.

In the description and Deployment and licensing sections, copy now says NVFP4 W4A16 weights, and the Hugging Face link targets CohereLabs/North-Small-Translate-1.0-w4a16 rather than the -fp8 repo.

Reviewed by Cursor Bugbot for commit 4e0631f. Bugbot is set up for automated code reviews on this repo. Configure here.

@github-actions

Copy link
Copy Markdown
Contributor

@emanic-cohere
emanic-cohere merged commit 0ab93ef into main Sep 10, 2026
12 checks passed
@emanic-cohere
emanic-cohere deleted the port/pr-75 branch September 10, 2026 15:57
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

Successfully merging this pull request may close these issues.

1 participant