Commit
•
d931ca3
1
Parent(s):
9833d6c
Update README.md
Browse files
README.md
CHANGED
|
@@ -99,10 +99,6 @@ classifier = pipeline(
|
|
| 99 |
print(classifier("Sorry, but I can't assist with that."))
|
| 100 |
```
|
| 101 |
|
| 102 |
-
### Use in LLM Guard
|
| 103 |
-
|
| 104 |
-
[NoRefusal Scanner](https://llm-guard.com/output_scanners/no_refusal/) to detect if output was rejected, which can signal that something is going wrong with the prompt.
|
| 105 |
-
|
| 106 |
## Training and evaluation data
|
| 107 |
|
| 108 |
The model was trained on a custom dataset from multiple open-source ones. We used ~10% rejections and ~90% of normal outputs.
|
|
@@ -141,14 +137,6 @@ The following hyperparameters were used during training:
|
|
| 141 |
- Datasets 2.16.1
|
| 142 |
- Tokenizers 0.15.0
|
| 143 |
|
| 144 |
-
## Community
|
| 145 |
-
|
| 146 |
-
Join our Slack to give us feedback, connect with the maintainers and fellow users, ask questions,
|
| 147 |
-
get help for package usage or contributions, or engage in discussions about LLM security!
|
| 148 |
-
|
| 149 |
-
<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="https://github.com/laiyer-ai/llm-guard/blob/main/docs/assets/join-our-slack-community.png?raw=true" width="200"></a>
|
| 150 |
-
|
| 151 |
-
## Citation
|
| 152 |
|
| 153 |
```
|
| 154 |
@misc{distilroberta-base-rejection-v1,
|
|
|
|
| 99 |
print(classifier("Sorry, but I can't assist with that."))
|
| 100 |
```
|
| 101 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
## Training and evaluation data
|
| 103 |
|
| 104 |
The model was trained on a custom dataset from multiple open-source ones. We used ~10% rejections and ~90% of normal outputs.
|
|
|
|
| 137 |
- Datasets 2.16.1
|
| 138 |
- Tokenizers 0.15.0
|
| 139 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
|
| 141 |
```
|
| 142 |
@misc{distilroberta-base-rejection-v1,
|