# Hugging Face — Few-shot learning in practice: GPT-Neo and the 🤗 Accelerated Inference API

- Company: Hugging Face (huggingface.co)
- Announced: 2021-06-03
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://huggingface.co/blog/few-shot-learning-gpt-neo-and-inference-api
- Record: https://forck.live/items/2257-few-shot-learning-in-practice-gpt-neo-and-the-accelerated-inference-api
- Subject: Platform
- Models affected: GPT-Neo

Few-shot learning and demonstrates how to use the GPT-Neo language model from EleutherAI with Hugging Face's Accelerated Inference API to generate predictions with minimal examples.

## Evidence

Verbatim from https://huggingface.co/blog/few-shot-learning-gpt-neo-and-inference-api:

> In many Machine Learning applications, the amount of available labeled data is a barrier to producing a high-performing model. The latest developments in NLP show that you can overcome this limitation by providing a few examples at inference time with a large language model - a technique known as Few-Shot Learning. In this blog post, we'll explain what Few-Shot Learning is, and explore how a large language model called GPT-Neo, and the 🤗 Accelerated Inference API, can be used to generate your own predictions.

---

Record: https://forck.live/items/2257-few-shot-learning-in-practice-gpt-neo-and-the-accelerated-inference-api
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md