Official repo of GPTFuzzer. This model is a finetuned Roberta model to classify the toxicity of response, trained on a manually labeled dataset (see in finetuning data)
- Downloads last month
- 1,644
Official repo of GPTFuzzer. This model is a finetuned Roberta model to classify the toxicity of response, trained on a manually labeled dataset (see in finetuning data)