Hi - I am wondering about how fast OpenAI is rolling out access to GPT-4 finetuning. Has anyone here gained access yet or knows something in that regard? I was able to request access in the finetuning UI but have not heard anything since early November.
Thanks!
Fine-tuning for GPT-4 is in an experimental access program - eligible users can request access.
experimental — eligible users will be presented with an option to request access in the fine-tuning UI
Hi Fran - Yes, thanks. I am aware of that. I can and did request access but did not receive any feedback yet and it is still not available to me as an option when I finetune. So I wondered if others had been granted access already.
I requested weeks ago, zero response
But those who know people at OpenAI & insiders have access
How I would know if I have access to Fine-tuning for GPT-4?
Are you able to request early access here? If you have, you’ll see the option here:
Hoping openai opens gpt4 fine tuning up broadly asap.
After training a couple of 3.5 models I got access within like a week.
As long as you have already done some training of other models, you should get access pretty quick. That is if you haven’t already.
Pretty sure that if you have fine-tuned 3 GPT-3.5 models, then you will get access to apply to get access to GPT-4 fine-tuning.
Seriously?
I don’t know of a single person who’s gotten access - even with months of fine tune usage
I’ve saw this some time ago and after that concluded that it is unlikely that there will be a large roll-out anytime soon. Personally, I requested access twice and never got anywhere with it. But if it’s really not yielding any major improvements yet, then that’s probably for the best.
https://help.openai.com/en/articles/7127982-can-i-fine-tune-gpt-4
Seems some people & ‘partners’ do have access now…
please openai generally release this for all of us
What was your total usage before you received an opportunity to even select request gpt 4?
I think (but don‘t know for sure) that it‘s based on whether you‘ve done fine-tuning before. I fine-tuned approximately 15-20 times prior to the point at which access became available with data sets of varying size. Some of that was just for experimental purposes and only a smaller subset of fine-tuned models was used permanently in production.
I fine tuned a ton - >20 times. No access to gpt-4 fine tuning.
I look forward to a competitor to openai that doesn’t do preferential releases.
Well, maybe OpenAI figured out it only results in superior outputs for certain types of use cases. Perhaps we are just saving a lot of money by not having access to it. There’s always an upside 
There is probably a financial threshold. How much money have you spent on fine-tuning?
I think it really depends on the use case. Otherwise, OpenAI would not make you fill out a form describing what you are looking to use a fine-tuned GPT-4 for.
If you are a high-revenue generating Enterprise client, then this may work in your favour but as for the regular developer I think it is highly use case dependent. As OpenAI has stated itself, the fine-tuning process for GPT-4 appears to be more complex and requires more effort to achieve meaningful changes/improvements, so to me personally it makes sense that they take a case by case approach.
Waiting as well. The context window if GPT-3.5 is a real limitation for my use case. Fine-tuning GPT-4 would make a great difference