Instructions to use cookiechips/KillSwitch_ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cookiechips/KillSwitch_ai with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="cookiechips/KillSwitch_ai")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cookiechips/KillSwitch_ai", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add model checkpoint: prompt_guard_best.pt (v1)
Browse filesUpload trained prompt safety classifier checkpoint.
- Base: microsoft/deberta-v3-base
- Best threshold: 0.95
- Intended use: prompt safety detection
- prompt_guard_best.pt +3 -0
prompt_guard_best.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8f87bc4e8f60d0b130ebd2058a50d84009d49edd9569a96b90287cefd53b30
|
| 3 |
+
size 737763434
|