精选理由
想 Fine-tune MiniMax M3 的话，Fireworks 现在直接支持 LoRA 和 DPO，还能自定义 RL 训练，省事不少。
MiniMax M3 模型现已可在 Fireworks 上进行训练。用户可通过托管 LoRA SFT 和 DPO 进行标准微调。Fireworks 还提供 Training API，支持自定义 SFT、DPO 和 RL 训练循环，包含检查点、滚动推理和适配器热加载功能。
原文 · Fireworks AI
The MiniMax M3 model is now available for training on Fireworks! You can use managed LoRA SFT and D...
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: app.fireworks.ai/models/firewor… github.com/fw-ai/cookbook… 💬 0 🔄 0 ❤️ 16 👀 979 📊 2 ⚡