Bee-8B-RL is an open-weight 8 billion parameter model fine-tuned with reinforcement learning. It supports advanced chat templates with image and video understanding capabilities. The model is designed for local or self-hosted inference and can be used via the Transformers library or compatible inference engines.
In the Foundation models & chat space, Bee 8B RL takes a focused approach. It focuses on providing an open, RL-tuned large language model for local inference and assistant applications. It is built as an open-source project for developers and AI researchers. Bee 8B RL is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
Behind Bee 8B RL is Open-Bee, and it first shipped in 2024. Development happens publicly on GitHub with 4.7k stars and 2 commits in the last 90 days. Among its 3 catalogued features are Chat Template, Reinforcement Learning, and Multi-modal Support.
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