v0.5.2
· One min read
- llama.cpp updated to b1132, GGUF format support and increase in the speed. The old file format is still supported but uses llama dadbed9.
- Added Falcon models support (only GGUF)
- Added mmap and mlock options
- Added template for RWKV-4
- Added prompt format text editor with multiline support
- Added tfs_z and typical_p sampling parameters
- UI Improvements
- Templates improvments
- Fix model rename
- Fixed some UI bugs that could cause the app to crash.
- Fix llama, replit token_to_str
- Fixed many errors on model loading.
- Fixed scrolling issue