Update README.md
Browse files
README.md
CHANGED
|
@@ -23,7 +23,7 @@ pipeline_tag: text-generation
|
|
| 23 |
<a href="https://github.com/agentica-project/rllm" style="margin: 2px;">
|
| 24 |
<img alt="Code" src="https://img.shields.io/badge/RLLM-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 25 |
</a>
|
| 26 |
-
<a href="https://
|
| 27 |
<img alt="Blog" src="https://img.shields.io/badge/Notion-%23000000.svg?style=for-the-badge&logo=notion&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 28 |
</a>
|
| 29 |
<a href="https://x.com/Agentica_" style="margin: 2px;">
|
|
@@ -68,6 +68,7 @@ DeepCoder generalizes better to long contexts than the base distilled model, due
|
|
| 68 |
| --- | --- | --- | --- |
|
| 69 |
| **DeepCoder-14B-Preview** | 45.6 | 57.9 | 60.6 |
|
| 70 |
| **DeepSeek-R1-Distill-Qwen-14B** | 50.2 | 53.0 | 53.0 |
|
|
|
|
| 71 |
A more detailed description of the training recipe can be found in our [blog post](https://www.google.com).
|
| 72 |
|
| 73 |
## Evaluation
|
|
@@ -98,6 +99,14 @@ This permissive license ensures that researchers, developers, and enthusiasts wo
|
|
| 98 |
- Our model is trained on top of [`DeepSeek-R1-Distill-Qwen-1.5B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
|
| 99 |
- Our work is done as part of [Berkeley Sky Computing Lab](https://skycomputing.berkeley.edu/) and [Berkeley AI Research](https://bair.berkeley.edu/).
|
| 100 |
|
| 101 |
-
## Citation
|
|
|
|
| 102 |
```bibtex
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
```
|
|
|
|
| 23 |
<a href="https://github.com/agentica-project/rllm" style="margin: 2px;">
|
| 24 |
<img alt="Code" src="https://img.shields.io/badge/RLLM-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 25 |
</a>
|
| 26 |
+
<a href="https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51" target="_blank" style="margin: 2px;">
|
| 27 |
<img alt="Blog" src="https://img.shields.io/badge/Notion-%23000000.svg?style=for-the-badge&logo=notion&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 28 |
</a>
|
| 29 |
<a href="https://x.com/Agentica_" style="margin: 2px;">
|
|
|
|
| 68 |
| --- | --- | --- | --- |
|
| 69 |
| **DeepCoder-14B-Preview** | 45.6 | 57.9 | 60.6 |
|
| 70 |
| **DeepSeek-R1-Distill-Qwen-14B** | 50.2 | 53.0 | 53.0 |
|
| 71 |
+
|
| 72 |
A more detailed description of the training recipe can be found in our [blog post](https://www.google.com).
|
| 73 |
|
| 74 |
## Evaluation
|
|
|
|
| 99 |
- Our model is trained on top of [`DeepSeek-R1-Distill-Qwen-1.5B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
|
| 100 |
- Our work is done as part of [Berkeley Sky Computing Lab](https://skycomputing.berkeley.edu/) and [Berkeley AI Research](https://bair.berkeley.edu/).
|
| 101 |
|
| 102 |
+
## Citation
|
| 103 |
+
|
| 104 |
```bibtex
|
| 105 |
+
@misc{deepcoder2025,
|
| 106 |
+
title={DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level},
|
| 107 |
+
author={Michael Luo, Sijun Tan, Roy Huang, Xiaoxiang Shi, Rachel Xin, Colin Cai, Ameen Patel, Alpay Ariyak, Qingyang Wu, Ce Zhang, Li Erran Li, Raluca Ada Popa, Ion Stoica, Tianjun Zhang},
|
| 108 |
+
howpublished={\url{https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51}},
|
| 109 |
+
note={Notion Blog},
|
| 110 |
+
year={2025}
|
| 111 |
+
}
|
| 112 |
```
|