Purposes utilizing the steady mannequin names for base GPT-3 fashions (ada, babbage, curie, davinci) will mechanically be upgraded to the brand new fashions listed above on January 4, 2024. The brand new fashions may also be accessible within the coming weeks for early testing by specifying the next mannequin names in API calls: ada-002, babbage-002, curie-002, davinci-002.
Builders utilizing different older completion fashions (akin to text-davinci-003) might want to manually improve their integration by January 4, 2024 by specifying gpt-3.5-turbo-instruct within the “mannequin” parameter of their API requests. gpt-3.5-turbo-instruct is an InstructGPT-style mannequin, skilled equally to text-davinci-003. This new mannequin is a drop-in substitute within the Completions API and will probably be accessible within the coming weeks for early testing.
Builders wishing to proceed utilizing their fine-tuned fashions past January 4, 2024 might want to fine-tune replacements atop the brand new base GPT-3 fashions (ada-002, babbage-002, curie-002, davinci-002), or newer fashions (gpt-3.5-turbo, gpt-4). As soon as this function is accessible later this yr, we’ll give precedence entry to GPT-3.5 Turbo and GPT-4 fine-tuning to customers who beforehand fine-tuned older fashions. We acknowledge that migrating off of fashions which can be fine-tuned by yourself information is difficult. We will probably be offering assist to customers who beforehand fine-tuned fashions to make this transition as easy as attainable.
Within the coming weeks, we’ll attain out to builders who’ve not too long ago used these older fashions, and can present extra data as soon as the brand new completion fashions are prepared for early testing.