Zamba2-1.2B-instruct is an instruction-tuned 1.2 billion parameter language model developed by Zyphra. It uses a hybrid architecture optimized for efficiency and is designed for text generation and following user instructions. The model is hosted on Hugging Face and supports local inference via the Transformers library.
In the Foundation models & chat space, Zamba2 1.2B Instruct takes a focused approach. It focuses on running high-quality instruction-tuned language models with low memory and compute requirements. Zamba2 1.2B Instruct is an open-source project aimed at developers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.
Zyphra builds and maintains Zamba2 1.2B Instruct, and it first shipped in 2023. The project is developed in the open on GitHub with 18.6k stars and 12 commits in the last 90 days.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match