MiMo-7B-RL is a 7 billion parameter model developed by Xiaomi. It has undergone reinforcement learning post-training to improve its instruction following, reasoning, and tool-calling abilities. The model is released on Hugging Face and supports standard chat and function-calling formats.
In the Foundation models & chat space, MiMo 7B RL takes a focused approach. It focuses on providing a capable, smaller open model with strong reasoning and tool-use capabilities. MiMo 7B RL is an open-source project aimed at developers. MiMo 7B RL is open source under the Apache-2.0 license. It ships for the web, the command line, and API, and it can be self-hosted.
It is developed by Xiaomi (China), and it first shipped in 2023. The project is developed in the open on GitHub with 31.3k stars and 3.7k commits in the last 90 days. Among its 3 catalogued features are Instruction Following, Tool Calling, and reasoning. It exposes integrations via a public API.
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