{"id":32512,"date":"2023-06-03T06:00:00","date_gmt":"2023-06-03T13:00:00","guid":{"rendered":"https:\/\/insidebigdata.com\/?p=32512"},"modified":"2023-05-30T14:23:08","modified_gmt":"2023-05-30T21:23:08","slug":"video-highlights-fine-tune-gpt-j-6b-in-under-3-hours-on-ipus","status":"publish","type":"post","link":"https:\/\/insidebigdata.com\/2023\/06\/03\/video-highlights-fine-tune-gpt-j-6b-in-under-3-hours-on-ipus\/","title":{"rendered":"Video Highlights: Fine Tune GPT-J 6B in Under 3 Hours on IPUs"},"content":{"rendered":"
\n
\"\"<\/figure><\/div>\n\n\n

Did you know you can run GPT-J 6B on Graphcore<\/a> IPU in the cloud? Following the now infamous leaked Google memo, there’s been a real storm in the AI world recently around smaller, open source language models, like GPT-J, that are cheaper and faster to fine-tune, run and perform just as well as larger models for many language tasks.\u00a0<\/p>\n\n\n\n

Graphcore offers two pre-trained, ready-made GPT-J notebooks ready to try today on IPUs in Paperspace cloud for fine-tuning and inference:<\/p>\n\n\n\n

Text entailment on IPU using GPT-J – Fine-tuning<\/a><\/p>\n\n\n\n

Text generation on IPU using GPT-J – Inference<\/a><\/p>\n\n\n\n

It takes around 2 hours 45 minutes to work through the GPT-J fine tuning notebook in its entirety on a 16-IPU platform – this will vary, of course, if you want to bring your own data for fine tuning, which is good to know to work out costs on Paperspace.<\/p>\n\n\n\n

If you want to use GPT-J in production, contact Graphcore to find out their special pricing or to try it much faster on a 64-IPU system which is coming soon to Paperspace.<\/p>\n\n\n\n

What is GPT-J? A powerful, efficient alternative to large language models (LLMs) such as GPT-3 and GPT-4 for many NLP tasks. Fine-tuning GPT-J lets you tailor the model for specific applications, using a task-relevant dataset. <\/p>\n\n\n\n

In the video presentation below, Graphcore engineer Sofia Liguori walks through the process of fine-tuning GPT-J 6B on a Paperspace Gradient notebook (Google Colab alternative), powered by Graphcore IPUs. Run the Paperspace Gradient Notebook – Fine tuning: text entailment on IPU using GPT-J. You can also use GPT-J for text generation (inference) on Paperspace. Run the Paperspace Gradient Notebook – Inference: text generation on IPU using GPT-J. Read more about the the benefits of GPT-J in the company’s blog Fine-tune GPT-J: effective GPT-4 alternative for many NLP tasks<\/a>. <\/p>\n\n\n\n

\n