OpenAI brings fine-tuning to GPT-3.5 Turbo


Share post:

OpenAI customers can now bring custom data to the lightweight version of GPT-3.5, GPT-3.5 Turbo — making it easier to improve the text-generating AI model’s reliability while building in specific behaviors.

OpenAI claims that fine-tuned versions of GPT-3.5 can match or even outperform the base capabilities of GPT-4, the company’s flagship model, on “certain narrow tasks.”

“Since the release of GPT-3.5 Turbo, developers and businesses have asked for the ability to customize the model to create unique and differentiated experiences for their users,” the company wrote in a blog post published this afternoon. “This update gives developers the ability to customize models that perform better for their use cases and run these custom models at scale.”

With fine-tuning, companies using GPT-3.5 Turbo through OpenAI’s API can make the model follow instructions, such as having it always respond in a given language, better. Or they can improve the model’s ability to consistently format responses (e.g. for completing snippets of code), as well as hone the “feel” of the model’s output, like its tone, so that it better fits a brand or voice.

In addition, fine-tuning enables OpenAI customers to shorten their text prompts to speed up API calls and cut costs. “Early testers have reduced prompt size by up to 90% by fine-tuning instructions into the model itself,” OpenAI claims in the blog post.

Fine-tuning currently requires prepping data, uploading the necessary files and creating a fine-tuning job through OpenAI’s API. All fine-tuning data must pass through a “moderation” API and a GPT-4-powered moderation system to see if it’s in conflict with OpenAI’s safety standards, says the company. But OpenAI plans to launch a fine-tuning UI in the future with a dashboard for checking the status of ongoing fine-tuning workloads.

Fine-tuning costs are as follows:

  • Training: $0.008 / 1k tokens
  • Usage input: $0.012 / 1k tokens
  • Usage output: $0.016 / 1k tokens

“Tokens” represent raw text — e.g. “fan,” “tas” and “tic” for the word “fantastic.” A GPT-3.5-turbo fine-tuning job with a training file of 100,000 tokens, or about 75,000 words, would cost around $2.40, OpenAI says.

In other news, OpenAI today made available two updated GPT-3 base models (babbage-002 and davinci-002), which can be fine-tuned as well, with support for pagination and “more extensibility.” As previously announced, OpenAI plans to retire the original GPT-3 base models on January 4, 2024.

OpenAI said that fine-tuning support for GPT-4 — which, unlike GPT-3.5, can understand images in addition to text — will arrive sometime later this fall, but didn’t provide specifics beyond that.

Source link

Lisa Holden
Lisa Holden
Lisa Holden is a news writer for LinkDaddy News. She writes health, sport, tech, and more. Some of her favorite topics include the latest trends in fitness and wellness, the best ways to use technology to improve your life, and the latest developments in medical research.

Recent posts

Related articles

GitHub launches passkey support into general availability

GitHub is formally launching its passkeys security feature into general availability, two months after first debuting it...

Banish cumulative graphs from your pitch deck

You know what’s really awesome? Watching founders pitch on the TechCrunch Disrupt stage as part of Startup...

Saregama eyes Pocket Aces acquisition in video push

Saregama is in talks to acquire Pocket Aces, three people familiar with the matter said, as the...

Encrypted email provider Proton has built its own CAPTCHA service

Proton, the Swiss company that develops privacy-focused online services such as email, has developed its very own...

YouTube to add AI creator tools to find music for videos, add dubs

YouTube is expanding its Creator Music Studio, announced last year, with new AI features in addition to...

Harness launches Gitness, an open-source GitHub competitor

Since its launch in 2017, Harness, the software delivery platform founded by AppDynamics co-founder and CEO Jyoti...

7 global investors discuss African tech post-Kauffman Fellows’ first summit on the continent

In 2020, Kauffman Fellows (KF), a prominent venture education program renowned for its extensive and well-established network...

Poland opens privacy probe of ChatGPT following GDPR complaint

OpenAI is facing another investigation into whether its generative AI chatbot, ChatGPT, complies with European Union privacy...