Jayi2424
/

HumorGen-7B

Text Generation

Model card Files Files and versions

Jayi2424 commited on Mar 30

Commit

8b2369b

·

verified ·

1 Parent(s): 1b71b77

Use paper title as link text

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ tags:
 A 7B humor generation model fine-tuned from [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) using the **Cognitive Synergy Framework** — six psychologically-grounded AI personas generate and rank joke candidates, and only the best make it into training data. The result is a compact model that outperforms Qwen-2.5-32B and GPT-OSS-120B on automated humor evaluation.
-> 📄 [Paper](https://edwardajayi.github.io/assets/papers/HumorGen_CSF.pdf) · **Edward Ajayi, Prasenjit Mitra** · Carnegie Mellon University Africa
 > BT rating **1083.9 · 59.5% win rate** on SemEval 2026 MWAHAHA
 ---

 A 7B humor generation model fine-tuned from [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) using the **Cognitive Synergy Framework** — six psychologically-grounded AI personas generate and rank joke candidates, and only the best make it into training data. The result is a compact model that outperforms Qwen-2.5-32B and GPT-OSS-120B on automated humor evaluation.
+> 📄 [HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation](https://edwardajayi.github.io/assets/papers/HumorGen_CSF.pdf)
 > BT rating **1083.9 · 59.5% win rate** on SemEval 2026 MWAHAHA
 ---