Commit
•
517e565
1
Parent(s):
202633d
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,7 @@ library_name: transformers
|
|
| 11 |
pipeline_tag: text-generation
|
| 12 |
tags:
|
| 13 |
- dpo
|
|
|
|
| 14 |
- preference
|
| 15 |
- ultrafeedback
|
| 16 |
license: mit
|
|
@@ -191,7 +192,7 @@ While we're working on fixing the original dataset (already narrowed down ~2K pr
|
|
| 191 |
|
| 192 |
## Prompt template
|
| 193 |
|
| 194 |
-
We use the same prompt template as [
|
| 195 |
|
| 196 |
```
|
| 197 |
<|system|>
|
|
|
|
| 11 |
pipeline_tag: text-generation
|
| 12 |
tags:
|
| 13 |
- dpo
|
| 14 |
+
- rlaif
|
| 15 |
- preference
|
| 16 |
- ultrafeedback
|
| 17 |
license: mit
|
|
|
|
| 192 |
|
| 193 |
## Prompt template
|
| 194 |
|
| 195 |
+
We use the same prompt template as [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta):
|
| 196 |
|
| 197 |
```
|
| 198 |
<|system|>
|