---
license: apache-2.0
---

# Eurus-2-7B-SFT

## Links

- 📜 [Blog]()
- 🤗 [PRIME Collection](https://huggingface.co/PRIME-RL)
- 🤗 [SFT Data](https://huggingface.co/datasets/PRIME-RL/Eurus-2-SFT-Data) 

## Introduction

Eurus-2-7B-SFT is fine-tuned from [Qwen2.5-Math-7B-Base](https://huggingface.co/Qwen/Qwen2.5-Math-7B) for its great mathematical capabilities. It trains on [Eurus-2-SFT-Data](https://huggingface.co/datasets/PRIME-RL/Eurus-2-SFT-Data), which is an action-centric chain-of-thought reasoning dataset.

We apply imitation learning (supervised finetuning) as a warmup stage to teach models to learn reasoning patterns, , serving as a starter model for [Eurus-2-7B-PRIME](https://huggingface.co/PRIME-RL/Eurus-2-7B-PRIME). 

## Usage

We apply tailored prompts for coding and math task:

**System Prompt**

```
\nWhen tackling complex reasoning tasks, you have access to the following actions. Use them as needed to progress through your thought process.\n\n[ASSESS]\n\n[ADVANCE]\n\n[VERIFY]\n\n[SIMPLIFY]\n\n[SYNTHESIZE]\n\n[PIVOT]\n\n[OUTPUT]\n\nYou should strictly follow the format below:\n\n[ACTION NAME]\n\n# Your action step 1\n\n# Your action step 2\n\n# Your action step 3\n\n...\n\nNext action: [NEXT ACTION NAME]\n
```

**Coding**

```
{question} + "\n\nWrite Python code to solve the problem. Present the code in \n```python\nYour code\n```\nat the end.
```

**Math**

```
{question} + "\n\nPresent the answer in LaTex format: \\boxed{Your answer}"
```

## Evaluation

After finetuning, the performance of our Eurus-2-7B-SFT is shown in the following figure.

![image-20241230162026156](./figures/performance.jpg)

## Citation

```
```