---
license: apache-2.0
base_model:
  - Qwen/Qwen2.5-Coder-7B-Instruct
datasets:
  - IIGroup/X-Coder-SFT-376k
language:
  - en
tags:
  - code
  - sft
  - competitive-programming
---

# X-Coder-SFT-Qwen2.5-7B

X-Coder-SFT-Qwen2.5-7B is a code generation model fine-tuned on fully synthetic instruction data, designed for competitive programming tasks. It can serve as the foundation for subsequent RLVR training.

## Model Description

- **Base Model**: [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
- **Training Method**: Supervised Fine-Tuning (SFT)
- **Training Data**: [IIGroup/X-Coder-SFT-376k](https://huggingface.co/datasets/IIGroup/X-Coder-SFT-376k)
- **Parameters**: 7B

## Training

SFT training can be performed using various frameworks such as [ms-swift](https://github.com/modelscope/ms-swift), [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory), or [Megatron-LM](https://github.com/NVIDIA/Megatron-LM). For training details and code, please refer to the [X-Coder GitHub repository](https://github.com/JieWu02/X-Coder).

### Training Hyperparameters

| Parameter | Value |
|-----------|-------|
| Base Model | Qwen/Qwen2.5-Coder-7B-Instruct |
| Training Type | Full Parameter |
| Epochs | 8 |
| Global Batch Size | 128 |
| Learning Rate | 5e-5 |
| Max Grad Norm | 1.0 |
| Max Length | 32768 |
| Torch Dtype | bfloat16 |
| DeepSpeed | Zero3 Offload (80GB VRAM) / Zero2 (142GB VRAM) |
| Packing | True (2x faster training, slightly worse performance) |

## Performance on LiveCodeBench v5.

![Results](results.png)

## Recommended Inference Parameters

| Parameter | Value |
|-----------|-------|
| temperature | 0.6 |
| top_p | 0.95 |
| top_k | 20 (or -1 to disable) |
| max_new_tokens | 32768 |

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "IIGroup/X-Coder-SFT-Qwen2.5-7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

prompt = "Write a Python function to solve the two sum problem."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.6,
    top_p=0.95,
    top_k=20,
    do_sample=True
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Related Models

- **RL Model**: [IIGroup/X-Coder-RL-Qwen2.5-7B](https://huggingface.co/IIGroup/X-Coder-RL-Qwen2.5-7B) - RLVR trained version achieving 62.9 on LiveCodeBench

## Citation

```bibtex
@misc{wu2026xcoderadvancingcompetitiveprogramming,
      title={X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests}, 
      author={Jie Wu and Haoling Li and Xin Zhang and Jiani Guo and Jane Luo and Steven Liu and Yangyu Huang and Ruihang Chu and Scarlett Li and Yujiu Yang},
      year={2026},
      eprint={2601.06953},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2601.06953}, 
}
```

## License

This project is licensed under the Apache License 2.0.