Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,62 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model:
|
| 4 |
+
- Qwen/Qwen2.5-72B
|
| 5 |
+
tags:
|
| 6 |
+
- code
|
| 7 |
+
- swebench
|
| 8 |
+
- software
|
| 9 |
+
- issue-resolving
|
| 10 |
+
---
|
| 11 |
+
<!-- # Kimi-Dev -->
|
| 12 |
+
|
| 13 |
+
<div align="center">
|
| 14 |
+
<img src="./assets/main_logo.png" alt="Kimi Logo" width="400" />
|
| 15 |
+
<h2><a href="https://moonshotai.github.io/Kimi-Dev/">
|
| 16 |
+
Introducing Kimi-Dev: <br>A Strong and Open-source Coding LLM for Issue Resolution</a></h2>
|
| 17 |
+
</a></h2>
|
| 18 |
+
<b>Kimi-Dev Team</b>
|
| 19 |
+
<br>
|
| 20 |
+
|
| 21 |
+
</div>
|
| 22 |
+
<div align="center">
|
| 23 |
+
<a href="">
|
| 24 |
+
<b>📄 Tech Report (Coming soon...)</b>
|
| 25 |
+
</a> |
|
| 26 |
+
<a href="https://github.com/MoonshotAI/Kimi-Dev">
|
| 27 |
+
<b>📄 Github</b>
|
| 28 |
+
</a>
|
| 29 |
+
</div>
|
| 30 |
+
<br>
|
| 31 |
+
<br>
|
| 32 |
+
|
| 33 |
+
<!-- https://github.com/MoonshotAI/Kimi-Dev -->
|
| 34 |
+
|
| 35 |
+
We introduce Kimi-Dev-72B, our new open-source coding LLM for software engineering tasks. Kimi-Dev-72B achieves a new state-of-the-art on SWE-bench Verified among open-source models.
|
| 36 |
+
|
| 37 |
+
- Kimi-Dev-72B achieves 60.4% performance on SWE-bench Verified. It surpasses the runner-up, setting a new state-of-the-art result among open-source models.
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
- Kimi-Dev-72B is optimized via large-scale reinforcement learning. It autonomously patches real repositories in Docker and gains rewards only when the entire test suite passes. This ensures correct and robust solutions, aligning with real-world development standards.
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
- Kimi-Dev-72B is available for download and deployment on Hugging Face and GitHub. We welcome developers and researchers to explore its capabilities and contribute to development.
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
<div align="center">
|
| 47 |
+
<img src="./assets/open_performance_white.png" alt="Kimi Logo" width="600" />
|
| 48 |
+
<p><b>Performance of Open-source Models on SWE-bench Verified.</b></p>
|
| 49 |
+
|
| 50 |
+
</div>
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
## Citation
|
| 54 |
+
```
|
| 55 |
+
@misc{kimi_dev_72b_2025,
|
| 56 |
+
title = {Introducing Kimi-Dev: A Strong and Open-source Coding LLM for Issue Resolution},
|
| 57 |
+
author = {{Kimi-Dev Team}},
|
| 58 |
+
year = {2025},
|
| 59 |
+
month = {June},
|
| 60 |
+
url = {\url{https://www.moonshot.cn/Kimi-Dev}}
|
| 61 |
+
}
|
| 62 |
+
```
|