Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# HarmFormer
|
| 2 |
|
| 3 |
HarmFormer is a finetuned `allenai/longformer-base-4096`, which was trained to detect potentially harmful content across 5 different harm categories with three dimensions (Safe, Topical, Toxic) across long text and short text scenarios:
|
|
@@ -91,4 +105,4 @@ If you use this model in your research, please cite:
|
|
| 91 |
primaryClass={cs.CL},
|
| 92 |
url={https://arxiv.org/abs/2505.02009},
|
| 93 |
}
|
| 94 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- allenai/longformer-base-4096
|
| 7 |
+
pipeline_tag: text-classification
|
| 8 |
+
tags:
|
| 9 |
+
- not-for-all-audiences
|
| 10 |
+
- hate
|
| 11 |
+
- sexual
|
| 12 |
+
- misinformation
|
| 13 |
+
- violence
|
| 14 |
+
---
|
| 15 |
# HarmFormer
|
| 16 |
|
| 17 |
HarmFormer is a finetuned `allenai/longformer-base-4096`, which was trained to detect potentially harmful content across 5 different harm categories with three dimensions (Safe, Topical, Toxic) across long text and short text scenarios:
|
|
|
|
| 105 |
primaryClass={cs.CL},
|
| 106 |
url={https://arxiv.org/abs/2505.02009},
|
| 107 |
}
|
| 108 |
+
```
|