docs: point the model links to the gs64 container (#642) - #644
Merged
Conversation
The README still sent newcomers to the older per-row int4 mirror (mateogrgic/GLM-5.2-colibri-int4-with-int8-mtp), which measures ~9pp worse on quality and causes the think-mode loops / never-terminating generations in #455. Point to the group-scaled (gs64) container that docs/quickstart.md already recommends, and explain why gs64 over per-row. Updates the English README plus the zh-CN / zh-TW / it variants and both docker READMEs. The historical experiment log keeps its original link (it records what was actually run). New: https://huggingface.co/mastouri/GLM-5.2-colibri-int4-g64-with-int8-mtp Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Keeps main internally consistent with the README fix — same doc-only HF link correction, no code changes. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #642. Docs-only, no code changes — safe to put on
mainwithout the other in-progress dev work.The README (+ zh-CN / zh-TW / it variants, both docker READMEs) and
docs/quickstart.mdstill recommended the older per-row int4 mirrormateogrgic/GLM-5.2-colibri-int4-with-int8-mtp. Per #455 / #579 that container measures ~9pp worse on quality and causes the think-mode loops / never-terminating generations; the group-scaled (gs64) container cured every failing case.Same fix already merged to
dev(#643); this is the doc-link change only, cherry-picked ontomain. Reported by @timwoelfle.