Fireworks AI(@FireworksAI_HQ)
GLM 5.1 from @Zai_org is now available on @FireworksAI_HQ Training Platform across the Managed and T...
7.2Score
TL;DR · AI 摘要
Fireworks AI 平台正式支持智谱 GLM 5.1 模型，提供 SFT/DPO 微调能力、200K 超长上下文窗口，专为长周期智能体编程微调优化，RL 训练即将上线。
核心要点
- GLM 5.1 已集成至 Fireworks AI 托管与 API 训练工作流
- 支持带智能默认参数的 SFT 和 DPO 微调，亦允许自定义损失函数
- 200K 上下文窗口显著增强长程代码生成与 agentic 编程微调能力
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- GLM 5.1 × Fireworks AI 训练支持
- 模型来源
- 智谱 Zai_org
- 训练能力
- SFT / DPO 微调
- 自定义损失函数
- 200K 上下文窗口
- 适用场景
- 长周期智能体编程微调
- RL 训练（即将上线）
金句 / Highlights
值得收藏与分享的关键句。
GLM 5.1 from @Zai_org is now available on @FireworksAI_HQ Training Platform across the Managed and Training API workflows.
Try SFT and DPO with smart defaults or your own custom loss function with a 200K context window
perfect for long-horizon agentic coding fine-tunes. RL coming soon.
#GLM#Fireworks AI#大模型微调#SFT#DPO
打开原文Try SFT and DPO with smart defaults or your own custom loss function with a 200K context window, perfect for long-horizon agentic coding fine-tunes. RL" / X
Fireworks AI on X: "GLM 5.1 from @Zai_org is now available on @FireworksAI_HQ Training Platform across the Managed and Training API workflows. Try SFT and DPO with smart defaults or your own custom loss function with a 200K context window, perfect for long-horizon agentic coding fine-tunes. RL" / X
Don’t miss what’s happening
GLM 5.1 from
is now available on
Training Platform across the Managed and Training API workflows. Try SFT and DPO with smart defaults or your own custom loss function with a 200K context window, perfect for long-horizon agentic coding fine-tunes. RL coming soon. Get started:
·
1
4
60
6