ChatGPT-Maker OpenAI Says Fine-Tuning for GPT-3.5 Turbo Now Available, Fine-Tuned Version Can Match or Outperform Base GPT-4-Level Capabilities

Fine-tuning allows businesses to make the model follow instructions better, like making outputs "terse" or always responding in a given language

ChatGPT-Maker OpenAI Says Fine-Tuning for GPT-3.5 Turbo Now Available, Fine-Tuned Version Can Match or Outperform Base GPT-4-Level Capabilities
ChatGPT Representational Image (Photo Credits: Pexels)

San Francisco, August 23:  OpenAI has announced that fine-tuning for GPT-3.5 Turbo is now available, with fine-tuning for GPT-4 coming this fall. "Developers can now run supervised fine-tuning to make this model perform better for their use cases," the company said in a blogpost on Tuesday. According to early tests, a fine-tuned version of GPT-3.5 Turbo can match, or even outperform, base GPT-4-level capabilities on certain narrow tasks.

OpenAI further noted that similar to all its application programming interfaces (APIs), data sent in and out of the fine-tuning API is owned by the customer and is not used by the company, or any other organisation, to train other models. Fine-tuning allows businesses to make the model follow instructions better, like making outputs "terse" or always responding in a given language". WhatsApp Feature List: From Chat Lock to Edit Option, 5 Exciting Features Launched by Meta-Owned Messaging App.

Fine-tuning improves the model's ability to consistently format responses -- a crucial aspect for applications demanding a specific response format, such as code completion or composing API calls," the company said. Also, businesses with a recognisable brand voice can use fine-tuning for the model to be more consistent with their tone.

In addition to increased performance, fine-tuning also enables businesses to shorten their prompts while ensuring similar performance. "Fine-tuning with GPT-3.5-Turbo can also handle 4k tokens -- double our previous fine-tuned models," OpenAI said. Pinterest New Feature Update: Photo-Sharing Platform to Launch New Teen Safety Features to Protect Users' Personal Space.

Also, early testers have reduced prompt size by up to 90 per cent by fine-tuning instructions into the model itself, speeding up each API call and cutting costs. The company further mentioned that the support for fine-tuning with function calling and "gpt-3.5-turbo-16k" will be coming later this fall.

(The above story first appeared on LatestLY on Aug 23, 2023 10:38 AM IST. For more news and updates on politics, world, sports, entertainment and lifestyle, log on to our website latestly.com).


You Might Also Like

OpenAI Announces Next Phase of Its Global ‘AI for Impact Accelerator Programme’ in India

Sam Altman-Run OpenAI Acquires ‘io’ AI Startup Founded by Ex-Apple Designer Jony Ive in USD 6.4 Billion Deal

Chegg Layoffs: US-Based Edtech Company To Cut 22% Workforce Amid Rise of AI Tools for Studies, Will Shut Down US Canada Services by End of 2025

Sam Altman-Run OpenAI Negotiates With Microsoft for New Billion-Dollar Deal and Future IPO, Says Report

Share Us