How to set gpt-4 model instead of gpt-4-0613

API
,
1

Hi, i am using GPT-4 model but the result giving me by openai is GPT-4-0613 :

image123
image123450Ă—785 110 KB

I noticed that this model is less performant than Chat GPT chat by example, probably using the GPT-4 model.

Do you know if there is a way to use the last GPT 4 model as ennounced here ?

Thanks

2

gpt-4-0613 is the snapshot of the GPT model as of 13/June. When you query the GPT 4 API, it is automatically sent to the lastest version of the model available to the API, which is the 06/13 one.

The model for ChatGPT on the other hand, is similar to gpt-4 but is trained a bit differently, hence the difference in performance

1 Like
3

Hey stephane, I’m facing the same issue. It’s a headache since GPT-4 as of today and GPT-4-0613 are different. Happens with one of my prompts that GPT-4 solves it properly and GPT-4-0613 doesn’t follows the system prompt. Tested on playground vs API.

OpenAI should provide a better handling of model versions.

4

I think you are suffering an illusion. Take your example of solve/not solve. Set the temperature and top_p to 0. You’re going to get the same result every time from a model call from the same input.

Then you just must replicate the settings. That includes every character or whitespace. Showing you the same token usage in the daily use log. Playground will give “example code” that shows the settings.

“gpt-4” gives you “gpt-4-0613” because the name is only an alias that points to the currently-recommended model, which continues to be updated.

2 Likes
5

Hey _j! I was controlling just temperature but not top_p. As you suggested, that fixes it and turns it deterministic.

Thanks, I wasn`t aware of top_p effect.

1 Like
6

Hi again!

Unfortunately it seem I’ve been fooled by randomness here. I tried to replicate but again stochastic behaviour showed. Sometimes works some other don’t.

Regarding the opening post, as you mentioned, it’s true there seems to be no difference
between GPT-4 and GPT-4-613. But within them even with temperature = 0 and top p 0.01 (cannot be set to 0), they are not fully deterministic. It seems something changes when reloading playground or api calling.

Since this is no more related with this post I’m going to open a new topic.