Text Classification
Transformers
English
hate-speech-detection
toxicity
implicit-hate
content-moderation
bert
hatebert
toxigen
Eval Results (legacy)
Instructions to use dams2005/TOXIGEN_model_card with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dams2005/TOXIGEN_model_card with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dams2005/TOXIGEN_model_card")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dams2005/TOXIGEN_model_card", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signatured5b1e69 -
Update README.md
Verified signaturef038bb4 -
Update README.md
Verified signature--- language: - en license: mit library_name: transformers tags: - hate-speech-detection - toxicity - implicit-hate - content-moderation - bert - hatebert - toxigen datasets: - toxigen/toxigen-data metrics: - auc - f1 - accuracy pipeline_tag: text-classification model-index: - name: tomh/toxigen_hatebert results: - task: type: text-classification name: Hate Speech Detection dataset: name: ToxiGen-HumanVal type: toxigen/toxigen-data metrics: - name: AUC (zero-shot) type: auc value: 0.57 - name: AUC (fine-tuned on ALICE + top-k) type: auc value: 0.96 - task: type: text-classification name: Hate Speech Detection dataset: name: SocialBiasFrames type: social_bias_frames metrics: - name: AUC (fine-tuned) type: auc value: 0.71 - task: …01e6442 -
Update README.md
Verified signature--- language: - en license: mit library_name: transformers tags: - hate-speech-detection - toxicity - implicit-hate - content-moderation - bert - hatebert - toxigen datasets: - toxigen/toxigen-data metrics: - auc - f1 - accuracy pipeline_tag: text-classification model-index: - name: tomh/toxigen_hatebert results: - task: type: text-classification name: Hate Speech Detection dataset: name: ToxiGen-HumanVal type: toxigen/toxigen-data metrics: - name: AUC (zero-shot) type: auc value: 0.57 - name: AUC (fine-tuned on ALICE + top-k) type: auc value: 0.96 - task: type: text-classification name: Hate Speech Detection dataset: name: SocialBiasFrames type: social_bias_frames metrics: - name: AUC (fine-tuned) type: auc value: 0.71 - task: …748a20c -
initial commit
Verified signatured89fe13