README.md

---
datasets:
- Alexhf825/dataset-AutoMR-pangu
language:
- en
metrics:
- accuracy
base_model:
- FreedomIntelligence/openPangu-Embedded-7B
---


# AutoMR for Pangu

This project equips the Pangu model with the AutoMR reasoning framework, optimized for Huawei Ascend hardware.

## 🌳 Project Structure

```
.
├── AMC.SH
├── automr
│   ├── config.py
│   ├── dag.py
│   ├── data_loader.py
│   ├── evaluator.py
│   ├── __init__.py
│   ├── model.py
│   ├── strategies.py
│   ├── trainer.py
│   └── utils.py
├── checkpoints
│   └── MATH
├── embedder_server.sh
├── generator_server.sh
├── main.py
├── math_train.sh
└── processed_data
    ├── AMC
    └── MATH
```

## 🔧 1. Installation

### a. Clone the Project Repository

```bash
hf download Alexhf825/AutoMR-pangu --local-dir AutoMR-pangu
cd AutoMR-pangu
```

### b. Install Dependencies
```
```

### c. Download Datasets

This command will download the datasets and place them in the `./processed_data` directory, matching the project structure.

```bash
hf download Alexhf825/dataset-AutoMR-pangu --repo-type=dataset --local-dir=./
```

## 🚀 2. Start the Servers

This project requires two services running in an OpenAI-API style. Please run the following commands in **two separate terminal sessions**.

**Start the Embedder Server:**

```bash
bash embedder_server.sh
```

**Start the Generator Server:**

```bash
bash generator_server.sh
```

## 📈 3. Run Evaluation

A pre-trained checkpoint (`MATH`) is provided. You can directly evaluate the model on the `AMC` dataset using the following command:

```bash
bash AMC.sh
```

## 🏋️ 4. Run Training

You can also train the model from scratch on the `MATH` dataset by running:

```bash
bash math_train.sh
```