eric/ericxliu-me
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

📚 Auto-publish: Add/update 5 blog posts
All checks were successful
Hugo Publish CI / build-and-deploy (push) Successful in 34s
Details

Browse Source 
Generated on: Sun Aug  3 03:19:53 UTC 2025
Source: md-personal repository
This commit is contained in:
Automated Publisher
2025-08-03 03:19:53 +00:00
parent 38bbe8cbae
commit 23b9adc43a
5 changed files with 121 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
content/posts/a-deep-dive-into-ppo-for-language-models.md
View File

@@ -1,6 +1,6 @@
---
title: "A Deep Dive into PPO for Language Models"
date: 2025-08-03T01:47:10
date: 2025-08-03T03:19:06
draft: false
---
@@ -9,7 +9,7 @@ Large Language Models (LLMs) have demonstrated astonishing capabilities, but out
You may have seen diagrams like the one below, which outlines the RLHF training process. It can look intimidating, with a web of interconnected models, losses, and data flows.
![[Pasted image 20250730232756.png]]
![](/images/a-deep-dive-into-ppo-for-language-models/64bfdb4b-678e-4bfc-8b62-0c05c243f6a9.png)
This post will decode that diagram, piece by piece. We'll explore the "why" behind each component, moving from high-level concepts to the deep technical reasoning that makes this process work.