Skip to content

Commit b56b68a

Browse files
committed
docs: improve readme
1 parent 7ec305f commit b56b68a

File tree

3 files changed

+93
-7
lines changed

3 files changed

+93
-7
lines changed

README.md

Lines changed: 92 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,24 @@
1-
# Coder-Pro
1+
<h1 align="center">
2+
<img src="assets/logo.png" alt="Anni Logo" width="100" />
3+
<br />
4+
Anni
5+
</h1>
26

3-
A Qwen-based code assistant fine-tuned for reasoning and solving data structures and algorithms tasks.
7+
<p align="center">
8+
<a href="https://huggingface.co/BigJuicyData/Anni" target="_blank"><img alt="Hugging Face"
9+
src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Anni-ffc107?color=ffc107&logoColor=white"/></a>
10+
<a href="https://modelscope.cn/models/quanteat/Anni" target="_blank">
11+
<img alt="ModelScope Model" src="https://img.shields.io/badge/🤖%20ModelScope-Anni-604ad3?color=604ad3"/>
12+
</a>
13+
<a href="https://github.com/CoderUni/CodingLLM/actions/workflows/codeql.yml">
14+
<img src="https://github.com/CoderUni/CodingLLM/actions/workflows/codeql.yml/badge.svg" alt="Build Status">
15+
</a>
16+
</a>
17+
</p>
18+
19+
<p align="center">
20+
<strong>Anni</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.
21+
</p>
422

523
---
624

@@ -16,25 +34,93 @@ A Qwen-based code assistant fine-tuned for reasoning and solving data structures
1634

1735
---
1836

19-
### License
37+
## 💻 Usage
38+
39+
**Get started immediately** using the provided Google Colab notebooks:
40+
41+
* **(Recommended) GGUF Inference :** Open the [Colab Notebook](https://colab.research.google.com/drive/16RKUtphbI1rAds_lLwPGk2cRhf9CDJDo?usp=sharing) to run standard inference.
42+
43+
* **vLLM Serving:** Open the [Colab Notebook](https://colab.research.google.com/drive/1lXYtLT729qcxJPc56TllgwiGEsjIiW0Q?usp=sharing) to run inference using the vLLM server.
44+
45+
---
46+
47+
## 🛠️ Development Setup
48+
49+
### Prerequisites
50+
51+
1. **Python Dependencies:**
52+
```bash
53+
pip install -r requirements.txt
54+
```
55+
2. **System Tools:**
56+
Ensure `tmux` is installed on your system (required for training scripts).
57+
58+
### Configuration
59+
60+
1. **Environment Variables:**
61+
Rename the example environment file and add your API tokens (WandB, HuggingFace, ModelScope).
62+
```bash
63+
mv config/example.env config/.env
64+
# Edit config/.env with your keys
65+
```
66+
67+
2. **Training Config:**
68+
Edit [config/config.yaml](config/config.yaml) to adjust hyperparameters.
69+
* *Note:* Specify the `LOCAL_STORAGE_PATH` in [src/train.py](src/train.py) before starting training.
70+
71+
### Running Training
72+
73+
To start the training process, run the shell script:
74+
75+
```bash
76+
./scripts/train.sh
77+
```
78+
79+
---
80+
81+
## 📂 Project Structure
82+
83+
### Source Code (`src/`)
84+
| File | Description |
85+
|------|-------------|
86+
| [`preprocess.py`](src/preprocess.py) | Downloads the [OpenCodeReasoning-2 dataset](https://huggingface.co/datasets/nvidia/OpenCodeReasoning-2) and preprocesses it for training. |
87+
| [`train.py`](src/train.py) | Downloads the base model and fine-tunes it on the preprocessed dataset. |
88+
| [`save.py`](src/save.py) | Loads the fine-tuned LoRA adapters and saves the model as merged 16-bit and GGUF formats. |
89+
| [`upload.py`](src/upload.py) | Uploads the merged model to Hugging Face and ModelScope. |
90+
91+
### Scripts (`scripts/`)
92+
| File | Description |
93+
|------|-------------|
94+
| [`train.sh`](scripts/train.sh) | Runs the training script with specified parameters. |
95+
| [`eval.sh`](scripts/eval.sh) | Evaluates the model on the LiveCodeBench dataset. |
96+
| [`serve.sh`](scripts/serve.sh) | Serves the model using the vLLM server. |
97+
| [`terminate_train.sh`](scripts/terminate_train.sh) | Terminates the training process. |
98+
99+
### Frontend (`web/`)
100+
The frontend code for Anni is available in the `web` directory.
101+
👉 **[View Frontend Documentation](web/README.md)**
102+
103+
---
104+
105+
## ⚖️ License
20106

21107
This repository’s **model and its training code** are released under the **MIT License**.
22108
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**.
23109

24110
---
25111

26-
### Training Dataset Notice
112+
## Training Dataset Notice
27113

28114
The training dataset includes openly licensed sources under **CC-BY-4.0**, which **permits commercial use with attribution**.
29115

30116
**Attribution:**
31117

32-
- OpenCoderReasoning-2 (CC-BY-4.0)
118+
- [OpenCoderReasoning-2](https://huggingface.co/datasets/nvidia/OpenCodeReasoning-2) (CC-BY-4.0)
33119

34120
> Note: The dataset itself is **not included** in this model release.
35121
---
36122

37-
### Disclaimer
123+
## Disclaimer
38124

39125
This model may generate incorrect or unsafe code.
40126
Evaluate and verify outputs before using in production.

assets/screenshot.png

110 KB
Loading

web/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -72,7 +72,7 @@ Open `.env` and configure it to match your vLLM setup:
7272
VLLM_URL="http://localhost:8000/v1"
7373
7474
# The specific model name you are serving (Must match vLLM config)
75-
VLLM_MODEL="BigJuicyData/coder-final"
75+
VLLM_MODEL="BigJuicyData/Anni"
7676
7777
# Context window limit
7878
VLLM_TOKEN_LIMIT="32000"

0 commit comments

Comments
 (0)