-
OpenAI has launched fine-tuning capabilities for GPT-4o, allowing developers to customise the AI model for specific use cases.
-
Fine-tuning enables developers to refine the model’s responses, adapt its tone and structure, and train it to follow complex instructions.
-
OpenAI is offering 1 million free training tokens per day for every organisation until September 23rd to encourage adoption.
OpenAI has announced the highly anticipated launch of fine-tuning capabilities for its powerful GPT-4o AI model. This move allows developers to customise GPT-4o using their own datasets to achieve superior performance and accuracy tailored to specific use cases. Fine-tuning empowers developers to refine the model’s responses, adapt its tone and structure, and even train it to follow complex, domain-specific instructions.
Early results indicate that significant improvements can be achieved with relatively small training datasets. OpenAI has showcased two impressive examples of GPT-4o fine-tuning in action: Cosine’s Genie, an AI software engineering assistant, and Distyl’s Text-to-SQL Model, which demonstrated exceptional performance in converting natural language to SQL queries. With fine-tuning, developers can unlock the full potential of GPT-4o and achieve state-of-the-art results in various domains.
GPT-4o fine-tuning is available to all developers on paid usage tiers through OpenAI’s fine-tuning dashboard. Training costs are set at $25 per million tokens, with inference priced at $3.75 per million input tokens and $15 per million output tokens. Fine-tuning is also available for the GPT-4o mini model, with 2 million free training tokens per day offered until September 23rd. As OpenAI continues to invest in expanding its model customisation options, developers can expect even more exciting possibilities in the future.
