This is a quantized version of Mistral-7B-Instruct-v0.2 using the AWQ method to 4-bit precision. It enables efficient local inference of the instruction-tuned Mistral model on consumer hardware with reduced VRAM usage while maintaining high performance. The model is hosted on Hugging Face and can be used with the Transformers library or compatible inference engines.
Mistral 7B Instruct is a Text generation project. It focuses on running large language models with reduced memory and compute requirements on local hardware. Mistral 7B Instruct is an open-source project aimed at developers. Mistral 7B Instruct is open source under the AGPL-3.0 license. It runs on the web, the command line, and API.
It is developed by TheBloke, and it first shipped in 2022. The project is developed in the open on GitHub with 47.5k stars and 140 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 6 similar projects. Among its 3 catalogued features are 4-bit Quantization, Instruction Tuned, and Mistral Architecture.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do