Update README.md
Browse files
README.md
CHANGED
|
@@ -211,6 +211,9 @@ python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
|
| 211 |
3. For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
|
| 212 |
4. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
|
| 213 |
|
|
|
|
|
|
|
|
|
|
| 214 |
## 7. License
|
| 215 |
This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
|
| 216 |
DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that:
|
|
|
|
| 211 |
3. For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
|
| 212 |
4. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
|
| 213 |
|
| 214 |
+
Additionally, we have observed that the DeepSeek-R1 series models tend to bypass thinking pattern (i.e., outputting "\<think\>\n\n\</think\>") when responding to certain queries, which can adversely affect the model's performance.
|
| 215 |
+
**To ensure that the model engages in thorough reasoning, we recommend enforcing the model to initiate its response with "\<think\>\n" at the beginning of every output.**
|
| 216 |
+
|
| 217 |
## 7. License
|
| 218 |
This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
|
| 219 |
DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that:
|