---
title: roberta-hate-speech-dynabench-r2-target
canonical_url: "https://www.modelscope.cn/models/facebook/roberta-hate-speech-dynabench-r2-target"
md_url: "https://www.modelscope.cn/models/facebook/roberta-hate-speech-dynabench-r2-target.md"
repository: facebook/roberta-hate-speech-dynabench-r2-target
last_updated: 2025-05-20
pipeline_tag: text-classification
tasks:
  - text-classification
model_type:
  - roberta
architectures:
  - RobertaForSequenceClassification
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task emb"
  - "vllm 0.9.2"
downloads: 332
stars: 0
---

# roberta-hate-speech-dynabench-r2-target

> roberta-hate-speech-dynabench-r2-target - facebook 在 ModelScope 开源的模型。The R2 Target model from Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection

facebook/roberta-hate-speech-dynabench-r2-target 是 ModelScope 魔搭社区上的text-classification模型，可用 deploy_task emb、vllm 0.9.2 部署。

- **Repository**: facebook/roberta-hate-speech-dynabench-r2-target
- **Tasks**: text-classification
- **Inference backends**: deploy_task emb, vllm 0.9.2
- **Downloads**: 332
- **Stars**: 0
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/roberta-hate-speech-dynabench-r2-target

---

# LFTW R2 Target

The R2 Target model from [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://arxiv.org/abs/2012.15761)

## Citation Information

```bibtex
@inproceedings{vidgen2021lftw,
  title={Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection},
  author={Bertie Vidgen and Tristan Thrush and Zeerak Waseem and Douwe Kiela},
  booktitle={ACL},
  year={2021}
}
```

Thanks to Kushal Tirumala and Adina Williams for helping the authors put the model on the hub!