Update README.md
Browse files
README.md
CHANGED
@@ -40,6 +40,7 @@ CardProjector is a specialized series of language models, fine-tuned to generate
|
|
40 |
- **Avoid adding a system prompt; all instructions should be contained within the user prompt** This tip from the official [Usage recommendations](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B#usage-recommendations) from the deepseek-r1 ReadMe. Believe me, it was written for a reason.
|
41 |
|
42 |
- **To ensure that the model engages in thorough reasoning, I recommend enforcing the model to initiate its response with "\<think\>\nOkay, user is asking me to create a new character card. Let's think in detail about what the final character should look like." at the beginning of every output.** This tip from the official [Usage recommendations](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B#usage-recommendations) from the deepseek-r1 ReadMe too.
|
|
|
43 |
For copy:
|
44 |
```plain text
|
45 |
<think>
|
|
|
40 |
- **Avoid adding a system prompt; all instructions should be contained within the user prompt** This tip from the official [Usage recommendations](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B#usage-recommendations) from the deepseek-r1 ReadMe. Believe me, it was written for a reason.
|
41 |
|
42 |
- **To ensure that the model engages in thorough reasoning, I recommend enforcing the model to initiate its response with "\<think\>\nOkay, user is asking me to create a new character card. Let's think in detail about what the final character should look like." at the beginning of every output.** This tip from the official [Usage recommendations](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B#usage-recommendations) from the deepseek-r1 ReadMe too.
|
43 |
+
|
44 |
For copy:
|
45 |
```plain text
|
46 |
<think>
|