RLHF pipeline for Hinge bio generation — human preferences → reward model → PPO alignment
-
Updated
Mar 23, 2026 - Jupyter Notebook
#
aipi590
Here are 2 public repositories matching this topic...
LoRA fine-tuning of LFM2.5-1.2B to improve spatial reasoning on StepGame — AIPI 590.03 Intelligent Agents, Project 1
jupyter-notebook pytorch lora spatial-reasoning fine-tuning llm unsloth aipi590 aipi590-intelligent-agents
-
Updated
Mar 19, 2026 - HTML
Improve this page
Add a description, image, and links to the aipi590 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the aipi590 topic, visit your repo's landing page and select "manage topics."