The N Implementation Details of RLHF with PPO (#1580)

* The N Implementation Details of RLHF with PPO * quick change * fix format * update * quick update * Update the_n_implementation_details_of_rlhf_with_ppo.md Co-authored-by: Pedro Cuenca <[email protected]> * Update the_n_implementation_details_of_rlhf_with_ppo.md Co-authored-by: Pedro Cuenca <[email protected]> * Update the_n_implementation_details_of_rlhf_with_ppo.md Co-authored-by: Pedro Cuenca <[email protected]> * remove * update blog.yml * Update _blog.yml Co-authored-by: Leandro von Werra <[email protected]> --------- Co-authored-by: Pedro Cuenca <[email protected]> Co-authored-by: Leandro von Werra <[email protected]>
huggingface · Oct 24, 2023 · 25bf01e · 25bf01e
1 parent da04037
commit 25bf01e
Show file tree

Hide file tree

Showing 3 changed files with 546 additions and 0 deletions.
diff --git a/_blog.yml b/_blog.yml
@@ -2979,3 +2979,13 @@
     - gradio
     - open-source
     - serverless
+
+- local: the_n_implementation_details_of_rlhf_with_ppo
+  title: "The N Implementation Details of RLHF with PPO"
+  author: vwxyzjn
+  thumbnail: /blog/assets/167_the_n_implementation_details_of_rlhf_with_ppo/thumbnail.png
+  date: October 24, 2023
+  tags:
+    - research
+    - rl
+    - rlhf
diff --git a/assets/167_the_n_implementation_details_of_rlhf_with_ppo/thumbnail.png b/assets/167_the_n_implementation_details_of_rlhf_with_ppo/thumbnail.png