Update README.md
Browse files
README.md
CHANGED
|
@@ -52,6 +52,7 @@ We slightly change their configs and tokenizers. Please use our setting to run t
|
|
| 52 |
2. **Avoid adding a system prompt; all instructions should be contained within the user prompt.**
|
| 53 |
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{}."
|
| 54 |
4. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
|
|
|
|
| 55 |
|
| 56 |
## License
|
| 57 |
This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
|
|
|
|
| 52 |
2. **Avoid adding a system prompt; all instructions should be contained within the user prompt.**
|
| 53 |
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{}."
|
| 54 |
4. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
|
| 55 |
+
5. The context limit of the llama 3.1 8b variant is 128k (131072)
|
| 56 |
|
| 57 |
## License
|
| 58 |
This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
|