Tools
The MiniMax M3 model is now available for training on Fireworks! You can use managed LoRA SFT and DPO for standard fine-tuning workflows, or…
The MiniMax M3 model is now available for training on Fireworks! You can use managed LoRA SFT and DPO for standard fine-tuning workflows, or the Fireworks Training API for custom SFT, DPO, and RL loop
The MiniMax M3 model is now available for training on Fireworks! You can use managed LoRA SFT and DPO for standard fine-tuning workflows, or the Fireworks Training API for custom SFT, DPO, and RL loops with checkpointing, rollout inference, and adapter hotloading. Get started: https://app.fireworks.ai/models/fireworks/minimax-m3 https://github.com/fw-ai/cookbook/tree/main/training
Related
- The hard part of reinforcement learning on a frontier model is the infrastructure that keeps training and inference numerically identical: z…
- MiniMax M2.7 is now on Together AI. Trained by letting it run its own RL loop, resulting in the highest open-source score on MLE Bench Lite.
Source: Fireworks AI (X) | 2026-07-21