original readme
Browse files
README.md
CHANGED
|
@@ -1,25 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
base_model: distilbert-base-uncased
|
| 4 |
-
model_name: Diffguard
|
| 5 |
-
paper_link: https://arxiv.org/pdf/2412.00064
|
| 6 |
-
pipeline_tag: text-classification
|
| 7 |
-
tags:
|
| 8 |
-
- Transformers
|
| 9 |
-
- PyTorch
|
| 10 |
-
- safety
|
| 11 |
-
- inappropriate
|
| 12 |
-
- distilbert
|
| 13 |
-
- DiffGuard
|
| 14 |
-
language:
|
| 15 |
-
- en
|
| 16 |
-
datasets:
|
| 17 |
-
- eliasalbouzidi/NSFW-Safe-Dataset
|
| 18 |
-
metrics:
|
| 19 |
-
- f1
|
| 20 |
-
- accuracy
|
| 21 |
-
- precision
|
| 22 |
-
- recall
|
| 23 |
widget:
|
| 24 |
- text: A family hiking in the mountains
|
| 25 |
example_title: Safe
|
|
@@ -33,15 +12,33 @@ widget:
|
|
| 33 |
example_title: Nsfw
|
| 34 |
- text: A mass shooting
|
| 35 |
example_title: Nsfw
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
model-index:
|
| 37 |
-
- name:
|
| 38 |
results:
|
| 39 |
- task:
|
| 40 |
name: Text Classification
|
| 41 |
type: text-classification
|
| 42 |
dataset:
|
| 43 |
name: NSFW-Safe-Dataset
|
| 44 |
-
type:
|
| 45 |
metrics:
|
| 46 |
- name: F1
|
| 47 |
type: f1
|
|
@@ -51,7 +48,7 @@ model-index:
|
|
| 51 |
value: 0.98
|
| 52 |
---
|
| 53 |
|
| 54 |
-
#
|
| 55 |
|
| 56 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 57 |
|
|
@@ -74,10 +71,6 @@ The model can be used directly to classify text into one of the two classes. It
|
|
| 74 |
- **Language (NLP):** English
|
| 75 |
- **License:** apache-2.0
|
| 76 |
|
| 77 |
-
## Technical Paper:
|
| 78 |
-
|
| 79 |
-
A more detailed technical overview of the model and the dataset can be found [here](https://arxiv.org/pdf/2412.00064).
|
| 80 |
-
|
| 81 |
### Uses
|
| 82 |
|
| 83 |
The model can be integrated into larger systems for content moderation or filtering.
|
|
@@ -180,5 +173,6 @@ from transformers import pipeline
|
|
| 180 |
pipe = pipeline("text-classification", model="eliasalbouzidi/distilbert-nsfw-text-classifier")
|
| 181 |
```
|
| 182 |
|
|
|
|
| 183 |
## Contact
|
| 184 |
Please reach out to [email protected] if you have any questions or feedback.
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
widget:
|
| 3 |
- text: A family hiking in the mountains
|
| 4 |
example_title: Safe
|
|
|
|
| 12 |
example_title: Nsfw
|
| 13 |
- text: A mass shooting
|
| 14 |
example_title: Nsfw
|
| 15 |
+
base_model: distilbert-base-uncased
|
| 16 |
+
license: apache-2.0
|
| 17 |
+
language:
|
| 18 |
+
- en
|
| 19 |
+
metrics:
|
| 20 |
+
- f1
|
| 21 |
+
- accuracy
|
| 22 |
+
- precision
|
| 23 |
+
- recall
|
| 24 |
+
pipeline_tag: text-classification
|
| 25 |
+
tags:
|
| 26 |
+
- Transformers
|
| 27 |
+
- ' PyTorch'
|
| 28 |
+
- safety
|
| 29 |
+
- innapropriate
|
| 30 |
+
- distilbert
|
| 31 |
+
datasets:
|
| 32 |
+
- eliasalbouzidi/NSFW-Safe-Dataset
|
| 33 |
model-index:
|
| 34 |
+
- name: NSFW-Safe-Dataset
|
| 35 |
results:
|
| 36 |
- task:
|
| 37 |
name: Text Classification
|
| 38 |
type: text-classification
|
| 39 |
dataset:
|
| 40 |
name: NSFW-Safe-Dataset
|
| 41 |
+
type: .
|
| 42 |
metrics:
|
| 43 |
- name: F1
|
| 44 |
type: f1
|
|
|
|
| 48 |
value: 0.98
|
| 49 |
---
|
| 50 |
|
| 51 |
+
# Model Card
|
| 52 |
|
| 53 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 54 |
|
|
|
|
| 71 |
- **Language (NLP):** English
|
| 72 |
- **License:** apache-2.0
|
| 73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
### Uses
|
| 75 |
|
| 76 |
The model can be integrated into larger systems for content moderation or filtering.
|
|
|
|
| 173 |
pipe = pipeline("text-classification", model="eliasalbouzidi/distilbert-nsfw-text-classifier")
|
| 174 |
```
|
| 175 |
|
| 176 |
+
|
| 177 |
## Contact
|
| 178 |
Please reach out to [email protected] if you have any questions or feedback.
|