README.md

---
language:
  - en
license: apache-2.0
tags:
  - text-generation
  - humor
  - computational-humor
  - peft
  - lora
  - qwen
  - cognitive-synergy-framework
  - headline-humor
base_model: Qwen/Qwen2.5-7B-Instruct
pipeline_tag: text-generation
---

# HumorGen GRPO — 7B

Part of the [HumorGen Collection](https://huggingface.co/collections/Jayi2424/humorgen) · SaLT Lab, Carnegie Mellon University

---

Offline Group Relative Policy Optimization (O-GRPO) on the SFT checkpoint. Trains on the full group of six persona candidates per headline rather than a single binary pair.

**Paper(s):** [arXiv:2604.09629](https://arxiv.org/abs/2604.09629)

---

## Training

| Property | Value |
|:---|:---|
| Stage | Offline Group Relative Policy Optimization (O-GRPO) |
| Initialized from | HumorGen_SFT_7B |
| Backbone | Qwen2.5-7B-Instruct (QLoRA 4-bit) |
| Group size | 6 (one per CSF persona) |
| Reward | HumorRank Bradley-Terry scores |

## Usage

This is a PEFT LoRA adapter. Load the base model and apply the adapter:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(model, "Jayi2424/HumorGen_GRPO_7B")

headline = "AI writes entire novel; readers say it felt a little too human"
prompt = (
    "<|im_start|>system\n"
    "You are a comedy writer. Write one sharp, witty joke for the headline.\n<|im_end|>\n"
    f"<|im_start|>user\n{headline}<|im_end|>\n"
    "<|im_start|>assistant\n"
)
inputs  = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=120, temperature=0.9, top_p=0.95)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Citation

```bibtex
@misc{ajayi2026humorgen,
  title         = {HumorGen: Cognitive Synergy for Humor Generation in Large Language
                   Models via Persona-Based Distillation},
  author        = {Ajayi, Edward and others},
  year          = {2026},
  eprint        = {2604.09629},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2604.09629}
}
```