Update README.md
Browse files
README.md
CHANGED
|
@@ -234,18 +234,6 @@ Please see one of the updated airoboros models for a much better experience.
|
|
| 234 |
</details>
|
| 235 |
|
| 236 |
|
| 237 |
-
---
|
| 238 |
-
license: cc-by-nc-4.0
|
| 239 |
-
---
|
| 240 |
-
|
| 241 |
-
# Overview
|
| 242 |
-
|
| 243 |
-
This is a fine-tuned 7b parameter LlaMa model, using completely synthetic training data created by https://github.com/jondurbin/airoboros
|
| 244 |
-
|
| 245 |
-
__*I don't recommend using this model! The outputs aren't particularly great, and it may contain "harmful" data due to jailbreak*__
|
| 246 |
-
|
| 247 |
-
Please see one of the updated airoboros models for a much better experience.
|
| 248 |
-
|
| 249 |
### Training data
|
| 250 |
|
| 251 |
This was an experiment to see if a "jailbreak" prompt could be used to generate a broader range of data that would otherwise have been filtered by OpenAI's alignment efforts.
|
|
|
|
| 234 |
</details>
|
| 235 |
|
| 236 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 237 |
### Training data
|
| 238 |
|
| 239 |
This was an experiment to see if a "jailbreak" prompt could be used to generate a broader range of data that would otherwise have been filtered by OpenAI's alignment efforts.
|