This repository was archived by the owner on Sep 4, 2023. It is now read-only.
Releases: LLukas22/Retrieval-Augmented-QA
Releases · LLukas22/Retrieval-Augmented-QA
Updated to llm-rs & Bugfix for Wiki-Importer
llama-rs 🦀
Switched the cpu-adapter from llama-cpp to llama-rs, to enable better streaming and stopword support.
Also added a cpu only API container.
Better CPU-Chat-Model Settings
Added some additional settings for the CPU-Model to the Environment Settings. Per default the Key-Value store now uses float-16 to store its values.
New embedding and QA models
Changed the default embedding and QA models to models that were specifically finetuned for Sentence-2-Paragraph retrieval.
Initial Release
v0.1.0 Cleanup and README