OpenAI has announced the availability of fine-tuning for GPT-3.5 Turbo, with fine-tuning for GPT-4 coming later this year. This update allows developers to customize models for their specific use cases and run them at scale. Early tests have shown that a fine-tuned version of GPT-3.5 Turbo can match or even outperform base GPT-4 on certain narrow tasks. Fine-tuning enables improved steerability, reliable output formatting, and custom tone, allowing businesses to create unique user experiences. It also allows for shorter prompts and can handle 4k tokens. Fine-tuning is most effective when combined with other techniques like prompt engineering and information retrieval. OpenAI ensures the safety of fine-tuning by passing training data through a moderation system. The pricing for fine-tuning includes training costs and usage costs. Additionally, OpenAI has introduced updated GPT-3 models (babbage-002 and davinci-002) as replacements for the original models, which will be turned off in 2024. These models can also be fine-tuned using the new API endpoint.
