DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
Paper • 1911.00536 • Published • 2
This is a paraphraser based on ceshine/t5-paraphrase-paws-msrp-opinosis and additionally fine-tuned on ParaNMT filtered for the task of detoxification.
The model was trained for the paper Text Detoxification using Large Pre-trained Neural Models.
An example of its use and the code for its training is given in https://github.com/skoltech-nlp/detox
- Downloads last month
- 26
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support