Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,17 @@ I am working on improving the model´s capabilities and will update the model if
|
|
| 17 |
|
| 18 |
A quantized GGML version for use with llama.cpp, kobold.cpp and other GUIs for CPU inference can be found [here](https://huggingface.co/jphme/vicuna-13b-v1.3-ger-GGML).
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## Results
|
| 21 |
|
| 22 |
I did only evaluate the output on a small, handcrafted sample on test prompts in German, confirming that the model's ability to understand and generate German text is above the base model in many situations.
|
|
|
|
| 17 |
|
| 18 |
A quantized GGML version for use with llama.cpp, kobold.cpp and other GUIs for CPU inference can be found [here](https://huggingface.co/jphme/vicuna-13b-v1.3-ger-GGML).
|
| 19 |
|
| 20 |
+
## Prompt Template
|
| 21 |
+
|
| 22 |
+
```
|
| 23 |
+
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
|
| 24 |
+
|
| 25 |
+
USER: Hello!
|
| 26 |
+
ASSISTANT: Hello!</s>
|
| 27 |
+
USER: How are you?
|
| 28 |
+
ASSISTANT: I am good.</s>
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
## Results
|
| 32 |
|
| 33 |
I did only evaluate the output on a small, handcrafted sample on test prompts in German, confirming that the model's ability to understand and generate German text is above the base model in many situations.
|