David Snelling
32df3ee6ae
- Add Q8 quantized models (75% smaller than FP32) - Enhance download scripts with model variant selection - Add smart model loading with availability detection - Implement runtime warnings for Q8 compatibility - Update documentation with Q8 usage examples - Maintain 100% backward compatibility (FP32 default) BREAKING CHANGE: None - FP32 remains default 🧠 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| buildEmbeddedPatterns.ts | ||
| check-patterns.cjs | ||
| create-models-release.sh | ||
| download-models.cjs | ||
| ensure-models.js | ||
| prepare-models.js | ||
| setup-github-models.sh | ||
| test-with-memory.sh | ||
| update-augmentations-metadata.sh | ||