4 months ago
Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering
Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering
Shamane Siriwardhana Rivindu Weerasekera Elliott Wen Suranga Nanayakkara
Abstract
In this paper, we illustrate how to fine-tune the entire Retrieval Augment Generation (RAG) architecture in an end-to-end manner. We highlighted the main engineering challenges that needed to be addressed to achieve this objective. We also compare how end-to-end RAG architecture outperforms the original RAG architecture for the task of question answering. We have open-sourced our implementation in the HuggingFace Transformers library.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| question-answering-on-squad-1 | RAG-end2end | Exact Match: 40.02 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.
AI Co-coding
Ready-to-use GPUs
Best Pricing
Hyper Newsletters
Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp