![Graphcore logo](https://user-images.githubusercontent.com/81682248/226963440-9cae0ac4-ebf5-407a-9870-5679e434cada.png)
Flan-T5 is the fine-tuned version of the T5 language model. Compared to T5, Flan-T5 has been fine-tuned on more than 1,000 additional tasks. This makes Flan-T5 a more efficient, open-source alternative to large language models like GPT-3 and GPT-4.
Try running Flan-T5 for yourself on the IPU (Intelligence Processing Unit), a completely new kind of massively parallel processor designed to accelerate machine intelligence. Access advanced, cost-efficient IPU compute on demand in the cloud via Paperspace notebooks to build, fine-tune and deploy AI models such as Flan-T5.
Notebook | Framework | Type | Try for Free |
---|---|---|---|
Flan-T5 is (probably) all you need | Hugging Face | Inference |
In this Paperspace notebook, you will learn how to use Flan-T5 for some common NLP tasks including text generation, sentiment analysis, advanced named entity recognition, question answering, intent classification, summarization and text classification.
Note: If you have an existing Flan-T5 application based on Hugging Face, you only need to change two lines of code to be able to run it on IPUs.
- Hugging Face models
- Overview blog
- How-to walkthrough blog
- Original paper
To find out more about running Flan-T5 on IPUs, or speak to an expert, please feel free to contact us.
Join our growing community and interact with AI experts, IPU developers and researchers. Hear the latest IPU news and get access to our newest models.
The contents of this repository are made available according to the terms of the Apache 2.0 licence. See the included LICENSE file for details.