From 3b439967f46293510f323d19e05c33d5a8016360 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 4 Nov 2024 16:00:27 +0100
Subject: [PATCH] =?UTF-8?q?=F0=9F=93=B0=20Update=20blog=20posts=20in=20doc?=
 =?UTF-8?q?umentation=20(#2319)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Bump dev version to `0.13.0.dev0`

* Update version number to 0.12 in CITATION.cff

* Add publication date to blog post

* 🧽 Fix judge documentation (#2318)

* Update judge examples and documentation

* without ':'

* Clean doc

* Fix typo in example code

* Add space after Attributes

* Update attribute name in judges.py

* Add installation instructions for llm-blender library

* Update PairRMJudge attributes documentation

* Fix return type in PairRMJudge

* Revert "🧽 Fix judge documentation (#2318)"

This reverts commit 337005d95169371935fb87f1c559c7412f8472a4.

* Update blog post publication dates

* revert to p5

* Update image URLs in index.mdx

* Sort and uniform thumbnail

* Update image alignment in index.mdx
---
 docs/source/index.mdx | 39 +++++++++++++++++++++++++--------------
 1 file changed, 25 insertions(+), 14 deletions(-)

diff --git a/docs/source/index.mdx b/docs/source/index.mdx
index b1de84afb1..bdddc9b6f2 100644
--- a/docs/source/index.mdx
+++ b/docs/source/index.mdx
@@ -38,28 +38,39 @@ Check the appropriate sections of the documentation depending on your needs:
 <div class="mt-10">
   <div class="w-full flex flex-col space-y-4 md:space-y-0 md:grid md:grid-cols-2 md:gap-y-4 md:gap-x-5">
     <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/dpo_vlm">
-      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/dpo_vlm/thumbnail.png" alt="thumbnail">
+      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/dpo_vlm/thumbnail.png" alt="thumbnail" class="mt-0">
+      <p class="text-gray-500 text-sm">Published on July 10, 2024</p>
       <p class="text-gray-700">Preference Optimization for Vision Language Models with TRL</p>
     </a>
-    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/rlhf">
-      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/120_rlhf/thumbnail.png" alt="thumbnail">
-      <p class="text-gray-700">Illustrating Reinforcement Learning from Human Feedback</p>
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/putting_rl_back_in_rlhf_with_rloo">
+      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/putting_rl_back_in_rlhf_with_rloo/thumbnail.png" alt="thumbnail" class="mt-0">
+      <p class="text-gray-500 text-sm">Published on June 12, 2024</p>
+      <p class="text-gray-700">Putting RL back in RLHF</p>
     </a>
-    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/trl-peft">
-      <img src="https://github.com/huggingface/blog/blob/main/assets/133_trl_peft/thumbnail.png?raw=true" alt="thumbnail">
-      <p class="text-gray-700">Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU</p>
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/trl-ddpo">
+      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/166_trl_ddpo/thumbnail.png" alt="thumbnail" class="mt-0">
+      <p class="text-gray-500 text-sm">Published on September 29, 2023</p>
+      <p class="text-gray-700">Finetune Stable Diffusion Models with DDPO via TRL</p>
+    </a>
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/dpo-trl">
+      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/157_dpo_trl/dpo_thumbnail.png" alt="thumbnail" class="mt-0">
+      <p class="text-gray-500 text-sm">Published on August 8, 2023</p>
+      <p class="text-gray-700">Fine-tune Llama 2 with DPO</p>
     </a>
     <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/stackllama">
-      <img src="https://github.com/huggingface/blog/blob/main/assets/138_stackllama/thumbnail.png?raw=true" alt="thumbnail">
+      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/138_stackllama/thumbnail.png" alt="thumbnail" class="mt-0">
+      <p class="text-gray-500 text-sm">Published on April 5, 2023</p>
       <p class="text-gray-700">StackLLaMA: A hands-on guide to train LLaMA with RLHF</p>
    </a>
-    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/dpo-trl">
-      <img src="https://github.com/huggingface/blog/blob/main/assets/157_dpo_trl/dpo_thumbnail.png?raw=true" alt="thumbnail">
-      <p class="text-gray-700">Fine-tune Llama 2 with DPO</p>
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/trl-peft">
+      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/133_trl_peft/thumbnail.png" alt="thumbnail" class="mt-0">
+      <p class="text-gray-500 text-sm">Published on March 9, 2023</p>
+      <p class="text-gray-700">Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU</p>
     </a>
-    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/trl-ddpo">
-      <img src="https://github.com/huggingface/blog/blob/main/assets/166_trl_ddpo/thumbnail.png?raw=true" alt="thumbnail">
-      <p class="text-gray-700">Finetune Stable Diffusion Models with DDPO via TRL</p>
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/blog/rlhf">
+      <img src="https://raw.githubusercontent.com/huggingface/blog/main/assets/120_rlhf/thumbnail.png" alt="thumbnail" class="mt-0">
+      <p class="text-gray-500 text-sm">Published on December 9, 2022</p>
+      <p class="text-gray-700">Illustrating Reinforcement Learning from Human Feedback</p>
     </a>
   </div>
 </div>