返回
原文
Nathan Lambert@natolambert
51AI 编辑部评分，满分 100
2026-08-04 22:58· 32分钟前
跳到正文
AI 摘要

Nathan Lambert 发布课程答疑视频，围绕后训练配方细节展开，涵盖能力分训后合并、RLVR 省略 KL 惩罚、约 1M SFT 提示词预算随模型规模扩展、RL 是否等同于带正则化的 SFT、内部轨迹训练与 ICL 处理、纯蒸馏继续预训练是否损害模型等 6 个问题。其课程将更聚焦于后训练主题。

Another quick q&a video as I wrap up the course soon. These ended up all being on various details in getting a post-training recipe right.

00：00 Intro 00：13 Q1： Should capabilities be trained separately， then merged？ 04：14 Q2： Why does RLVR often omit the KL penalty？ 05：58 Q3： How does the ~1M SFT prompt budget scale with model size？ 08：11 Q4： Is RL just SFT with a regularization term？ 11：01 Q5： In-house traces： train into the weights， or handle with ICL？ 12：44 Q6： Can distillation-only continued pretraining make a model worse？

PS I'm going through and rebranding the course more tightly just around post-training. Just because my book title is RLHF doesn't mean I need to title my course that！ Cheers & thanks for sending feedback.

教程/实践数据/训练
在 X 查看原推导出 Markdown
返回
51导出 Markdown
Nathan Lambert · @natolambert · X·2026-08-04 22:58·32分钟前
在 X 看原推· x.com
AI 摘要

Nathan Lambert 发布课程答疑视频，围绕后训练配方细节展开，涵盖能力分训后合并、RLVR 省略 KL 惩罚、约 1M SFT 提示词预算随模型规模扩展、RL 是否等同于带正则化的 SFT、内部轨迹训练与 ICL 处理、纯蒸馏继续预训练是否损害模型等 6 个问题。其课程将更聚焦于后训练主题。

Another quick q&a video as I wrap up the course soon. These ended up all being on various details in getting a post-training recipe right.

00：00 Intro 00：13 Q1： Should capabilities be trained separately， then merged？ 04：14 Q2： Why does RLVR often omit the KL penalty？ 05：58 Q3： How does the ~1M SFT prompt budget scale with model size？ 08：11 Q4： Is RL just SFT with a regularization term？ 11：01 Q5： In-house traces： train into the weights， or handle with ICL？ 12：44 Q6： Can distillation-only continued pretraining make a model worse？

PS I'm going through and rebranding the course more tightly just around post-training. Just because my book title is RLHF doesn't mean I need to title my course that！ Cheers & thanks for sending feedback.

教程/实践数据/训练
在 X 查看原推x.com