chore(gallery): add Index-Translate 9B variants - #12464
Open
localai-org-maint-bot wants to merge 2 commits into
Open
localai-org-maint-bot wants to merge 2 commits into
localai-org-maint-bot wants to merge 2 commits into
Conversation
1 of 2 tasks
Add Q4_K_M and Q8_0 builds for text translation with llama.cpp. Use the embedded template, disable thinking, and document installation. Pin the downloads and verify their SHA256 against HF metadata and headers. Assisted-by: Codex:gpt-6
Duplicate the socket descriptor before handing it to the activation helper. Close the original file to prevent its finalizer from closing a reused coverage descriptor after the helper closes its own file wrapper. Assisted-by: Codex:gpt-6
localai-org-maint-bot
force-pushed
the
cron/model-gallery-20261004
branch
from
October 4, 2026 03:06
929c14b to
63a4054
Compare
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Add Index-Translate-9B, a Qwen3.5-based text translation model, with Q4_K_M and Q8_0 GGUF variants for llama.cpp. Use the embedded template, thinking disabled, temperature 0, and a 32K context. Document installation and translation instructions.
This is the dense 9B model; #12444 adds the separate 35B-A3B model.
Notes for Reviewers
Downloads from mradermacher are pinned to revision
6537a9d04a02397200903eee74634eec8b78ebd6. Both SHA256 values match LFS metadata and the pinned download's x-linked-etag header:5ff8911559a6736d926183fcb20e2548416b589033660dd530d059c7b74e2c3289efba722c7fab5439a98c8062c1365879470215453dd19d7406bd7fcf0b0dacRange inspection confirms qwen35 architecture, 442 tensors per build, standard quantization types, and a template supporting disabled thinking. The pinned llama.cpp source supports qwen35. These entries configure text translation. Full inference and local hashing of complete weights were not run.
Validation:
go test ./core/gallery -count=1 -ginkgo.focus='gallery/index.yaml|gallery variant lint': passes.git diff --check: passes.go test ./core/gallery -count=1: 453 passed, 3 failed, 9 skipped. Unchanged master reproduces the same three failures from Forbidden GitHub/gist fixtures.Based on freshly fetched master
6c718fdda.Signed commits