README.md

---
license: mit
library_name: transformers
pipeline_tag: text-generation
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
datasets:
- zjunlp/KnowRL-Train-Data
---

<div align="center">
<h1 align="center"> KnowRL </h1>
<h3 align="center"> Exploring Knowledgeable Reinforcement Learning for Factuality </h3>

<p align="center">
  <a href="https://arxiv.org/abs/2506.19807">📄arXiv</a> •
  <a href="https://github.com/zjunlp/KnowRL">💻GitHub Repo</a> •
  <a href="https://huggingface.co/datasets/zjunlp/KnowRL-Train-Data">📖Dataset</a>
</p>
</div>

---

## Model Description

**KnowRL-DeepSeek-R1-Distill-Qwen-7B** is a slow-thinking language model that results from applying our **KnowRL** framework to the base model `DeepSeek-R1-Distill-Qwen-7B`.

The **KnowRL (Knowledgeable Reinforcement Learning)** framework is designed to mitigate hallucinations in Large Language Models (LLMs) by integrating external knowledge directly into the training process. The model is trained using **Knowledgeable Reinforcement Learning (RL)**, where a reward signal explicitly encourages factual accuracy in its reasoning process, helping it learn its own knowledge boundaries.

As a result, this model demonstrates a significant reduction in hallucinations on factual benchmarks while preserving or even enhancing the strong reasoning capabilities inherited from its base model.

## How to Use

### Using the `transformers` Library

You can use this model with the `transformers` library for text generation tasks. It is important to follow the specific prompt format, which includes `<think>` and `<answer>` tags, to get the best results.

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

# Set the device
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the model and tokenizer
model_name = "zjunlp/KnowRL-DeepSeek-R1-Distill-Qwen-7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).to(device)

# Define the prompt using the model's template
prompt = "What is the main function of the mitochondria?"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Generate a response
inputs = tokenizer(text, return_tensors="pt").to(device)
outputs = model.generate(**inputs, max_new_tokens=512)

# Decode and print the output
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
```
### Using `huggingface-cli`
You can also download the model from the command line using `huggingface-cli`.

```bash
huggingface-cli download zjunlp/KnowRL-DeepSeek-R1-Distill-Qwen-7B --local-dir KnowRL-DeepSeek-R1-Distill-Qwen-7B
```

## Training Details

The model is trained using Knowledgeable Reinforcement Learning (RL) (specifically GRPO) using data from the `zjunlp/KnowRL-Train-Data`.

For complete details on the training configuration and hyperparameters, please refer to our [GitHub repository](https://github.com/zjunlp/KnowRL).

---

## Citation
If you find this model useful in your research, please consider citing our paper:
```bibtex
@article{ren2025knowrl,
  title={KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality},
  author={Ren, Baochang and Qiao, Shuofei and Yu, Wenhao and Chen, Huajun and Zhang, Ningyu},
  journal={arXiv preprint arXiv:2506.19807},
  year={2025}
}
```