Fireworks Training Platform continues to expand.
TL;DR · AI 摘要
Fireworks AI宣布其训练平台新增GLM 5.1 LoRA RL功能，支持SFT、DPO和完整RL。
核心要点
- GLM 5.1 LoRA RL支持SFT、DPO和完整RL训练
- 200K上下文窗口提升模型处理能力
- 无使用上限和信用额度限制
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）
- Fireworks AI训练平台更新
- 新增功能
- GLM 5.1 LoRA RL
- 支持训练方式
- SFT
- DPO
- 完整RL
- 用户优势
- 200K上下文窗口
- 无使用上限
金句 / Highlights
值得收藏与分享的关键句。
GLM 5.1 LoRA RL支持SFT、DPO和完整RL训练，提供200K上下文窗口。
无使用上限和信用额度限制，用户可自由选择自定义损失函数或智能默认值。
Fireworks AI的训练平台持续扩展，为用户提供更灵活的模型训练方案。
Today GLM 5.1 LoRA RL is now live via Training API: SFT, DPO, and full RL on a 200K context window → custom loss functions or smart defaults. No usage ceilings. No credits to claim. Your model. Your inference. Get started →" / X
Fireworks AI on X: "Fireworks Training Platform continues to expand. Today GLM 5.1 LoRA RL is now live via Training API: SFT, DPO, and full RL on a 200K context window → custom loss functions or smart defaults. No usage ceilings. No credits to claim. Your model. Your inference. Get started →" / X
Don’t miss what’s happening
Fireworks Training Platform continues to expand. Today GLM 5.1 LoRA RL is now live via Training API: SFT, DPO, and full RL on a 200K context window → custom loss functions or smart defaults. No usage ceilings. No credits to claim. Your model. Your inference. Get started → http://fireworks.ai/train
Quote
ClaudeDevs
@ClaudeDevs
·
May 13
Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK
·
1
2
25
5