---
base_model: Qwen/Qwen3-4B-Base
datasets: stanfordnlp/imdb
library_name: transformers
model_name: pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base
tags:
- generated_from_trainer
- ppo
- trl
licence: license
---

# Model Card for pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base

This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the [stanfordnlp/imdb](https://huggingface.co/datasets/stanfordnlp/imdb) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).

## Quick start

```python
from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mxcui-none/huggingface/runs/g0u5t0a4) 



This model was trained with PPO, a method introduced in [Fine-Tuning Language Models from Human Preferences](https://huggingface.co/papers/1909.08593).

### Framework versions

- TRL: 1.4.0
- Transformers: 5.9.0
- Pytorch: 2.11.0+cu128
- Datasets: 4.8.6.dev0
- Tokenizers: 0.22.2

## Citations

Cite PPO as:

```bibtex
@article{mziegler2019fine-tuning,
    title        = {{Fine-Tuning Language Models from Human Preferences}},
    author       = {Daniel M. Ziegler and Nisan Stiennon and Jeffrey Wu and Tom B. Brown and Alec Radford and Dario Amodei and Paul F. Christiano and Geoffrey Irving},
    year         = 2019,
    eprint       = {arXiv:1909.08593}
}
```

Cite TRL as:
    
```bibtex
@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}
```