Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ The dataset used to fine-tune this model is available [here](https://huggingface
|
|
| 25 |
|
| 26 |
This model was fine-tuned with a fork of FastChat, and therefore uses the standard vicuna template:
|
| 27 |
```
|
| 28 |
-
USER: [prompt] ASSISTANT:
|
| 29 |
```
|
| 30 |
|
| 31 |
The most important bit, to me, is the context obedient question answering support, without extensive prompt engineering.
|
|
|
|
| 25 |
|
| 26 |
This model was fine-tuned with a fork of FastChat, and therefore uses the standard vicuna template:
|
| 27 |
```
|
| 28 |
+
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. USER: [prompt] ASSISTANT:
|
| 29 |
```
|
| 30 |
|
| 31 |
The most important bit, to me, is the context obedient question answering support, without extensive prompt engineering.
|