feat: Qwen3.5 と gemma4 モデルサポート追加#22
Open
shigel wants to merge 3 commits into
Open
Conversation
Ollama v0.18.2でツール呼び出し修正(#14605)がマージ済みのため、 Qwen3.5モデル定義を全モデル選択ロジックに追加。 - MODEL_CONTEXT_SIZES: 全7サイズ (0.8b〜122b-a10b), 256Kコンテキスト - MODEL_TIERS: 適切なティア・RAM要件で配置 - _SIDECAR_CANDIDATES: qwen3.5をqwen3より優先 - RAMフォールバック: 16GB→qwen3.5:9b, 8GB→qwen3.5:2b - install.sh: モデル選択・サイズ表示を更新 - テスト: ティア・コンテキスト・サイドカー・フォールバック等12件追加 Refs ochyai#19 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix test_vram_zero_falls_back_to_ram to expect qwen3.5:2b (new default) - Add qwen3.5:latest to MODEL_TIERS and _CONTEXT_WINDOWS as alias for 9b
vibe-coder.py に5モデル登録 (Tier B/D/E): - gemma4:31b, gemma4:26b (256K ctx, Vision) - gemma4:e4b, gemma4:latest, gemma4:e2b (128K ctx, Vision/Audio) 24GB+ 環境で gemma4:26b が自動選択される動作を含め、 context size / tier 整合性 / 自動検出の4テストを追加。
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
install.shの自動推奨を Qwen3 → Qwen3.5 系に更新（16GB+ →qwen3.5:9b、32GB+ サイドカーをqwen3.5:9bに）Changes
vibe-coder.pyMODEL_CONTEXT_SIZES/MODEL_TIERSに Qwen3.5 と gemma4 を追加install.shtests/test_vibe_coder.pyTest plan
pytest tests/test_vibe_coder.py— 全テストパス（gemma4 関連 4 件含む）gemma4:26bが自動選択されることを実機確認qwen3.5:9bがinstall.shから提案されることを確認