This is a 4-bit GPTQ quantized version of the Phi-3-mini-4k-instruct model. It enables efficient local inference of a capable small language model on consumer hardware. The model supports instruction following and can be used with standard Transformers pipelines or other inference frameworks.
In the Text generation space, Phi 3 Mini 4k Instruct takes a focused approach. It focuses on running capable language models with significantly reduced memory and compute requirements on local hardware. It is built as an open-source project for developers and researchers. The project is open source (Open Source). It runs on the web, the command line, and API.
It is developed by kaitchup. Among its 4 catalogued features are 4-bit quantization, instruction tuned, and efficient inference.
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