Update README.md
Browse filesadding benchmark image
README.md
CHANGED
|
@@ -48,10 +48,6 @@ library_name: transformers
|
|
| 48 |
---
|
| 49 |
|
| 50 |
# DeepSeek-R1-0528 Model Card
|
| 51 |
-
<!-- markdownlint-disable first-line-h1 -->
|
| 52 |
-
<!-- markdownlint-disable html -->
|
| 53 |
-
<!-- markdownlint-disable no-duplicate-header -->
|
| 54 |
-
|
| 55 |
<div align="center">
|
| 56 |
<img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
|
| 57 |
</div>
|
|
@@ -97,7 +93,7 @@ library_name: transformers
|
|
| 97 |
The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro.
|
| 98 |
|
| 99 |
<p align="center">
|
| 100 |
-
<img width="80%" src="figures/benchmark.png">
|
| 101 |
</p>
|
| 102 |
|
| 103 |
Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has increased from 70% in the previous version to 87.5% in the current version. This advancement stems from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question.
|
|
@@ -245,4 +241,4 @@ This code repository is licensed under [MIT License](LICENSE). The use of DeepSe
|
|
| 245 |
```
|
| 246 |
|
| 247 |
## 7. Contact
|
| 248 |
-
If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).
|
|
|
|
| 48 |
---
|
| 49 |
|
| 50 |
# DeepSeek-R1-0528 Model Card
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
<div align="center">
|
| 52 |
<img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
|
| 53 |
</div>
|
|
|
|
| 93 |
The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro.
|
| 94 |
|
| 95 |
<p align="center">
|
| 96 |
+
<img width="80%" src="https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/resolve/main/figures/benchmark.png">
|
| 97 |
</p>
|
| 98 |
|
| 99 |
Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has increased from 70% in the previous version to 87.5% in the current version. This advancement stems from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question.
|
|
|
|
| 241 |
```
|
| 242 |
|
| 243 |
## 7. Contact
|
| 244 |
+
If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).
|