b9012
📦 llama-cppView on GitHub →
✨ 1 features🐛 2 fixes🔧 1 symbols
Summary
This release introduces support for Mistral format yarn apply_scale and fixes bugs related to misunderstood boolean parameters during model conversion.
Migration Steps
- Update the conversion script by incorporating changes from convert_hf_to_gguf.py.
✨ New Features
- Added support for Mistral format yarn apply_scale.
🐛 Bug Fixes
- Fixed an issue where boolean parameters were misunderstood in the conversion process.
- Fixed Mistral format apply_scale support.