Chat Completion API vs Chat Playground Settings

[ervins21]

Hi,

I’m seeing high variations in outputs between the Chat Completion API (gpt-3.5-turbo) and the Chat Playground. Correct me if I’m wrong, but they should be near identical with temperature set to 0.

The chat playground is set to:

• Temperature: 0
• Top P: 1
• Freq Penalty: 0
• Presence Penalty: 0

Does anyone know what I should pass through in the API to exactly match the Playground settings. There are some inconsistencies. For example, Presence Penalty range in Playground is 0 to 1. While in API documentation, the range is from -2 to 2, with a default of 0.

TLDR: Should my API presence penalty be 0 or -2 to match Playground setting of 0.

Thanks!

[PaulBellow]

Welcome to the forum!

ChatGPT: Completions API doesn't reply as the web chat playground does?

Hi see the copy pasted conversation with ChatGPT : come ti chiami? Non ho un nome, sono solo un modello di linguaggio addestrato da OpenAI. Sono qui per rispondere alle tue domande e fornirti informazioni generali su una vasta gamma di argomenti. Se hai altre domande, non esitare a chiedere. what is your name? As I mentioned before, I am a large language model trained by OpenAI and do not have a name. I am designed to assist with a wide range of tasks, including answering questions a…

Playground output is different from API response

From Playground with following settings, I am getting interview questions one by one. { “model”: “text-davinci-003”, “prompt”: “I want you to act as an interviewer. I will be the candidate and you will ask me the interview questions for the position salesforce developer. I want you to only reply as the interviewer. Do not write all the conversation at once. I want you to only do the interview with me. Ask me the questions and wait for my answers. Ask me the questions one by one like an interv…

How to get the same or at least similar results between playground and API

Hello community, I’m going here for advice. I’m quite newbie in python (but I’m still to learn). I have created script which generate Wordpress articles with openai api. Basicly this script “text_render” values from csv file what is input. In csv file I have main keyword , keyword for images , keyword for subtitle 1-X… The key is get long creative paraghraphs (some)without injected start and end sentences with davinci-003 as I can get from playground. I use 1000 max tokens, 0.95 temperature I…

[lmartingam]

Tu peux me proposer un exercice en français niveau B1 sur le vocabulaire de l’ART et les LOISIRS?

[Ekaraj]

Hello,
I really need your help to prepare a quotation of freelancing and draft a quotation