Fine tuned model giving different results in playground and api

[sps]

Please use this tutorial to get started with consuming the fine-tuned chat completion model.

Build your own AI assistant in 10 lines of code - Python

This tutorial will guide you to develop a chat assistant with gpt-3.5-turbo accessible via the console. Prerequisites Before starting, you will need to have: Python 3.7.1 or higher installed on your system An OpenAI API key Step 1: Install the OpenAI Python Library First, we need to install the latest Python client library (currently v0.27.0) for the OpenAI API. You can install it using pip, the Python package manager, with the following command: pip install openai Step 2: Set Up Your O…

Also from screenshot you shared, it isn’t clear if you’re passing any system message.

I can see that on playground the temperature is set to 1 while in code it’s 0.

I also want to point out that getting deterministic responses at temperature = 1 is not possible in my knowledge.