The 9 billion parameter instruction-tuned (IT) version of Google's Gemma 2 model, optimized by Unsloth for faster training and inference. It includes a custom chat template and is distributed in formats suitable for Hugging Face and local runtimes. Popular for both inference and continued fine-tuning.
Gemma 2 9b It sits in PulseGate's Foundation models & chat category. It focuses on providing a fast, memory-efficient version of Google's Gemma 2 9B model for local and fine-tuning use. It is built as an open-source project for developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API, and it can be self-hosted.
Behind Gemma 2 9b It is Unsloth, and it first shipped in 2023. Development happens publicly on GitHub with 68.7k stars and 1.2k commits in the last 90 days. PulseGate's similarity index places it among 17 comparable projects. Key capabilities include Instruction Tuned, Chat Template, and Unsloth Optimized.
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