What is the inner fine-tuning strategy used for fine-tuning api, full parameter tuning or LoRA tuning? I’m recent doing experiments using fine-tuning api and this matters a lot for my research. :pray:

Fine-tuning strategy, full parameter tuning or LoRA?

_j May 27, 2024, 3:23pm 2

You can read about PPO, however, OpenAI won’t comment on their technology officially.

1 Like

Topic		Replies	Views
Is Fine-tuning a technical Fine-tuning? API fine-tuning	1	198	January 15, 2025
Which fine tuning algorithms are offered? API fine-tuning , openai-documentation	0	102	April 16, 2025
Fine-Tuning: What is happening under the hood? API api	0	398	February 11, 2024
Is the GPT 3.5 fine-tuning service prompt tuning? Community gpt-35-turbo , chatgpt , fine-tuning	8	4766	September 13, 2023
Parameter efficient fine tuning with open ai models API	0	603	July 11, 2023