Anni

<h1 align="center"> <img src="assets/logo.png" alt="Anni Logo" width="100" /> <br /> Anni </h1> <p align="center"> <a href="https://huggingface.co/BigJuicyData/Anni" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Anni-ffc107?color=ffc107&logoColor=white"/></a>&nbsp;<a href="https://modelscope.cn/models/quanteat/Anni" target="_blank"><img alt="ModelScope Model" src="https://img.shields.io/badge/🤖%20ModelScope-Anni-604ad3?color=604ad3"/></a>&nbsp;<a href="https://github.com/CoderUni/Anni"><img src="https://img.shields.io/badge/GitHub-CoderUni%2FAnni-181717?style=flat&logo=github&logoColor=white" alt="GitHub Repo"></a> </p> <p align="center"> <strong><a href="https://github.com/CoderUni/Anni">Anni</a></strong> is a high-performance code assistant built upon the <strong>Qwen3 14B</strong> architecture. Fine-tuned on the <strong>OpenCodeReasoning-2</strong> dataset, Anni is engineered to excel in deep algorithmic reasoning, competitive programming logic, and the implementation of complex, high-efficiency data structures. </p>

---

🚀 Model Overview

---

💻 Usage

Get started immediately using the provided Google Colab notebooks:

• (Recommended) GGUF Inference : Open the Colab Notebook to run standard inference.

• vLLM Serving: Open the Colab Notebook to run inference using the vLLM server.

---

🛠️ Development Setup

Prerequisites

1. Python Dependencies:

   pip install -r requirements.txt
   

2. System Tools: Ensure tmux is installed on your system (required for training scripts).

Configuration

1. Environment Variables: Rename the example environment file and add your API tokens (WandB, HuggingFace, ModelScope).

   mv config/example.env config/.env
   # Edit config/.env with your keys
   

2. Training Config: Edit config/config.yaml to adjust hyperparameters.

   • Note: Specify the LOCAL_STORAGE_PATH in src/train.py before starting training.

Running Training

To start the training process, run the shell script:

./scripts/train.sh

---

📂 Project Structure

Source (src/)

Scripts (scripts/)

Frontend (web/)

The frontend code for Anni is available in the web directory. 👉 View Frontend Documentation

---

⚖️ License

This repository’s model and its training code are released under the MIT License.
All other elements, such as frontend code, project name and logo, are trademarks of the developer and owner of this repository (Hans) and may not be used without explicit permission.

---

📚 Training Dataset Notice

The training dataset includes openly licensed sources under CC-BY-4.0, which permits commercial use with attribution.

Attribution:

• OpenCoderReasoning-2 (CC-BY-4.0)

Note: The dataset itself is not included in this model release.

---

⚠️ Disclaimer

This model may generate incorrect or unsafe code. Evaluate and verify outputs before using in production.