diff --git a/.image_mappings/a-deep-dive-into-ppo-for-language-models.txt b/.image_mappings/a-deep-dive-into-ppo-for-language-models.txt index 6ca76b2..be508d1 100644 --- a/.image_mappings/a-deep-dive-into-ppo-for-language-models.txt +++ b/.image_mappings/a-deep-dive-into-ppo-for-language-models.txt @@ -1 +1,2 @@ Pasted image 20250730232756.png|64bfdb4b-678e-4bfc-8b62-0c05c243f6a9.png +Pasted image 20250816140700.png|.png diff --git a/content/posts/a-comprehensive-guide-to-breville-barista-pro-maintenance.md b/content/posts/a-comprehensive-guide-to-breville-barista-pro-maintenance.md index 1bdd444..c8d2058 100644 --- a/content/posts/a-comprehensive-guide-to-breville-barista-pro-maintenance.md +++ b/content/posts/a-comprehensive-guide-to-breville-barista-pro-maintenance.md @@ -1,6 +1,6 @@ --- title: "A Comprehensive Guide to Breville Barista Pro Maintenance" -date: 2025-08-16T21:07:33 +date: 2025-08-16T21:13:14 draft: false --- diff --git a/content/posts/a-deep-dive-into-ppo-for-language-models.md b/content/posts/a-deep-dive-into-ppo-for-language-models.md index e5eb7e3..08e4498 100644 --- a/content/posts/a-deep-dive-into-ppo-for-language-models.md +++ b/content/posts/a-deep-dive-into-ppo-for-language-models.md @@ -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 20250816140700.png]] +![](/images/a-deep-dive-into-ppo-for-language-models/.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. diff --git a/static/images/a-deep-dive-into-ppo-for-language-models/.png b/static/images/a-deep-dive-into-ppo-for-language-models/.png new file mode 100644 index 0000000..2d74573 Binary files /dev/null and b/static/images/a-deep-dive-into-ppo-for-language-models/.png differ