Mind Lab - Macaron
We develop our in-house RL platform that supports up to 1T-parameter LLMs with high efficiency and low cost, and improve three key agentic capabilities of LLMs with RL.
MinT Mind Lab Toolkit MinT (Mind Lab Toolkit) is an RL infrastructure that helps agents and models learn from real experience. It abstracts away compute scheduling, distributed rollout, and training orchestration so teams can iterate learning loops inside real tasks with real feedback under real product constraints. MinT provides a unified and reproducible way to run reinforcement learning across multiple models and tasks, with a strong focus on making LoRA RL simple, stable, and efficient for both mainstream and frontier scale models. You define what to train, what data to learn from,…
saved by
related reading
- Macaron-V1-Preview: 749B MoL Agent Model post-trained from GLM5.1macaron.im
- LoRA Without Regret - Thinking Machines Labthinkingmachines.ai
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- On-Policy Distillation - Thinking Machines Labthinkingmachines.ai
- Thinking Machines Labthinkingmachines.ai
- A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
- Tinkerthinkingmachines.ai
- Democratizing frontier AI R&D to accelerate science and technologymirendil.com
- RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
- Together AI | The AI Native Cloudtogether.ai
- Data lab to train frontier models & evaluate agents | micro1micro1.ai
- Forge: Scalable Agent RL Framework and Algorithm - MiniMax News | MiniMaxminimax.io