Better Question-Answering Models on a Budget
This work addresses the challenge of making sophisticated conversational AI more accessible and cost-effective for users with limited budgets, though it is incremental as it builds on existing methods like LoRA and known datasets.
The paper tackled the problem of improving question-answering models efficiently by fine-tuning smaller OPT models using LoRA and the Stanford Alpaca dataset, achieving performance comparable to models three times larger at a cost of only 40 USD in compute.
Low-rank adaptation (LoRA) and question-answer datasets from large language models have made it much easier for much smaller models to be finetuned to the point where they display sophisticated conversational abilities. In this paper, we present Eluwa, a family of LoRA models that use the Stanford Alpaca dataset and massively improve the capabilities of Facebook's OPT 1.3B, 2.7B and 6.7B models. We benchmark these models in multiple ways, including letting GPT-4 judge their answers to prompts that span general knowledge, writing, programming and other tasks. We show that smaller models here can be fine-tuned to be as performant as models 3x larger - all for as little as 40 USD in compute.