Name | Modified | Size | Downloads / Week |
---|---|---|---|
Parent folder | |||
KolosalAI_Installer.exe | 2025-02-13 | 11.2 MB | |
kolosal_win64_avx2_vulkan_0.1.5.zip | 2025-02-13 | 11.0 MB | |
README.md | 2025-02-13 | 614 Bytes | |
v0.1.5 source code.tar.gz | 2025-02-13 | 10.2 MB | |
v0.1.5 source code.zip | 2025-02-13 | 10.4 MB | |
Totals: 5 Items | 42.9 MB | 0 |
What's Changed
- Context shifting with StreamingLLM (https://arxiv.org/abs/2309.17453) to unlimited generation
- Llimit max context to 4096 to make it more memory efficient and faster
- Added stop generation
- Added regenerate button
- Redesign progress bar
- Model loading handled asyncrhonously
- Added unload model button
- Huge refactor
- Fix code block rendering glitches
- Setting max new tokens to 0 will result in unlimited generation with context shifting
- Fix application crash when delete a chat
Full Changelog: https://github.com/Genta-Technology/Kolosal/compare/v0.1.4.1...v0.1.5