精选理由
DeepSeek V4 Flash 0731在Fireworks微调，支持SFT/DPO/RL，成本低
Fireworks 宣布 DeepSeek V4 Flash 0731 开放微调。用户可通过 Dedicated Training API 运行 SFT、DPO 和 RL 训练任务。SFT 与 DPO 也能在托管界面中操作。该模型面向编码智能体和高吞吐生产场景，官方称以远低于同类方案的成本提供强质量。
原文 · Fireworks AI
DeepSeek V4 Flash 0731 is ready to fine-tune on Fireworks. Run SFT, DPO, and RL training jobs on th...
DeepSeek V4 Flash 0731 is ready to fine-tune on Fireworks. Run SFT, DPO, and RL training jobs on the Dedicated Training API. SFT and DPO from the managed UI. Built for coding agents and high-volume production. Strong quality at a fraction of the cost. docs.fireworks.ai/fine-tuning/mo… 💬 0 🔄 1 ❤️ 12 👀 378 📊 2 ⚡