MiniCPM-2B-sft-bf16 is a 2-billion parameter instruction fine-tuned language model developed by OpenBMB. It uses a custom chat template and is designed for efficient deployment on consumer hardware. The model excels at dialogue and instruction following despite its compact size and is distributed on Hugging Face.
In the Foundation models & chat space, MiniCPM 2B Sft takes a focused approach. It focuses on delivering capable language model performance in a small 2B parameter footprint suitable for edge devices. It is built as an open-source project for developers. The project is open source (Apache-2.0). MiniCPM 2B Sft is available on the web and the command line, and it can be self-hosted.
OpenBMB builds and maintains MiniCPM 2B Sft, and it first shipped in 2024. Development happens publicly on GitHub with 26k stars and 26 commits in the last 90 days. Among its 3 catalogued features are Instruction Tuning, Lightweight LLM, and Chat Format.
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