README.md

---
base_model:
- meta-llama/Meta-Llama-3-8B
datasets:
- IgnoraZ/SynthQuestions
language:
- en
license: cc-by-4.0
library_name: transformers
pipeline_tag: text-generation
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This is the model from the paper **From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding**.

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Model type:** Chat Model
- **Language(s) (NLP):** English
- **License:** CC-BY-4.0
- **Finetuned from model:** LLaMA-3-8B
- **Finetuned with data:**  1M dataset from `IgnoraZ/SynthQuestions`

For more details like hyper-parameters, please refer to our paper.

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/Ignoramus0817/SynthQuestions
- **Paper:** https://www.arxiv.org/abs/2506.03968

## How to Get Started with the Model

This is a model in HF format, which can be deployed with common inference frameworks like Transformers, vLLM, SGLang and so on.

We finetuned it with custom chat template instead of the default one from LLaMA. **Please make sure to use the chat template in the `tokenizer_config.json` when inferring.**

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Alignment Benchmarks
|     Model      | Arena Hard (WR%) | Alpaca Eval 2.0 (LC) |
| :------------: | :--------------: | :------------------: |
| SynthQuestions |       15.4       |        18.87         |


### Closed-form Benchmarks
|     Model      | IFEVAL | MMLU  | ARC-C | GPQA | GSM8K | MATH  |
| :------------: | :----: | :---: | :---: | :--: | :---: | :---: |
| SynthQuestions | 57.05  | 65.79 | 63.92 | 30.3 | 70.53 | 22.71 |

## Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

```
@misc{zhu2025realsyntheticsynthesizingmillions,
      title={From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding}, 
      author={Chiwei Zhu and Benfeng Xu and Xiaorui Wang and Zhendong Mao},
      year={2025},
      eprint={2506.03968},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.03968}, 
}
```

## Model Card Contact

Please contact tanz@mail.ustc.edu.cn.