Land the full open-weight stack on main - #29
Merged
Merged
Conversation
The stacked PRs merged into each other's base branches instead of main; this brings their combined content onto main in one commit: Gemma-4 E4B/E2B/12B, Kimi-VL-A3B, GLM-4.6V-Flash, Qwen3.8-27B, Qwen3.5-2B/0.8B/4B, Kimi K3, the shared-config alignment and refreshed leaderboard scores, the think-block guard, and a top-10 README leaderboard (full table stays in leaderboard.csv).
boyang-zhang1
force-pushed
the
land-oss-stack
branch
from
August 26, 2026 22:30
5478e6e to
fc67d5e
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The stacked PRs #16–#26 merged into each other's base branches instead of main (their bases were never retargeted), so main stopped at #15 and the newer models never reached the published leaderboard. This branch contains the entire chain — Gemma-4 E4B/E2B/12B, Kimi-VL-A3B, GLM-4.6V-Flash, Qwen3.8-27B, Qwen3.5-2B/0.8B/4B, Kimi K3, the config alignment + refreshed scores from #26, and the think-block guard — plus one new commit that limits the README leaderboard to the top 10 systems (the full 30-system table stays in leaderboard.csv).