0.1.0

facebookresearch/tribev20.1.0Jul 23, 2023by 1b5d

AI Summary

This release marks the initial version of Trieve v2, introducing a Hugging Face generic model and upgrading llama.cpp to support newer models like Llama 2. Additionally, the project streamlines its Docker deployment by consolidating images into a default lightweight version and a GPU-enabled option, alongside general stability improvements.

Key Highlights

Introduction of Hugging Face generic model support
Upgrade to llama.cpp enabling Llama 2 compatibility
Streamlined Docker deployment with two images (default and GPU)
General stability improvements and bug fixes

New Features

Hugging Face generic model integration
Llama 2 model support
GPU-enabled Docker image

Full Release Notes

- Introducing Huggingface generic model, which can be used to run many popular models on HF
- Upgrade llama.cpp in order to run newer Llama models like Llama 2
- Streamline docker images down to 2 images: a default lightweight one, and a gpu enabled image with nvidia / cuda support
- General fixes and stability improvements