Skip to content

Latest commit

 

History

History
9 lines (5 loc) · 426 Bytes

README.md

File metadata and controls

9 lines (5 loc) · 426 Bytes

Customer-Support-Responses

This project aims to build a model that can generate automated responses to customer queries using a sequence-to-sequence (seq2seq) model or a transformer-based model like BART (Bidirectional and Auto-Regressive Transformers).

Dataset We use the Customer Support Responses dataset from Hugging Face: Customer-Support-Responses.

results/: Directory to save model checkpoints and other results.