Repository navigation
feat: map Qwen/Qwen3.6-27B to the qwen3.6 renderer - #196
Open
sdtblckgov wants to merge 1 commit into
Open
sdtblckgov wants to merge 1 commit into
sdtblckgov wants to merge 1 commit into
Conversation
Qwen3.6-27B ships the same chat template and tokenizer config as Qwen3.6-35B-A3B (byte-identical on the Hub). Add it to MODEL_RENDERER_MAP, MULTIMODAL_MODELS and the Qwen3.5-family enable_thinking defaults, and to the parity catalog. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Maps
Qwen/Qwen3.6-27Bto the existingqwen3.6renderer. Without this, it falls back to the default renderer, and callers have to set the renderer name by hand.Qwen3.6-27B ships the same chat template and tokenizer config as
Qwen3.6-35B-A3B, byte-identical on the Hub, as are the FP8 variants. So this adds it to:MODEL_RENDERER_MAPMULTIMODAL_MODELSenable_thinkingdefaultstests/parity.pyFull test suite passes locally (14,349 tests), and ruff is clean.
Context: we train Qwen3.6-27B LoRA through prime-rl and currently pass
renderer.name=qwen3.6explicitly.🤖 Generated with Claude Code
Note
Add
Qwen/Qwen3.6-27Bto the qwen3.6 rendererRegisters Qwen/Qwen3.6-27B in
MODEL_RENDERER_MAPandMODEL_MODALITIESin renderers/base.py, mirroring the existing Qwen3.6-35B-A3B entries._ENABLE_THINKING_DEFAULTSin renderers/qwen35.py withenable_thinkingdefaulting to true.MODEL_CATALOGin tests/parity.py, with shared-template and roundtrip suites disabled.Macroscope summarized 98b31dd.