gpt-35-turbo

Version: 703844
This model can be deployed for both inference and fine-tuning purposes. Model family: GPT-3.5 The gpt-35-turbo (also known as ChatGPT) is the most capable and cost-effective model in the GPT-3.5 family which has been optimized for chat using the Chat Completions API. It is a language model designed for conversational interfaces and the model behaves differently than previous GPT-3 models. Previous models were text-in and text-out, meaning they accepted a prompt string and returned a completion to append to the prompt. However, the ChatGPT model is conversation-in and message-out. The model expects a prompt string formatted in a specific chat-like transcript format and returns a completion that represents a model-written message in the chat. This model supports 4097 max input tokens and training data is up to Sep 2021.
GPT-3.5 Turbo now supports fine-tuning, allowing developers and businesses to customize the model for specific applications.
You can use GPT-3.5 Turbo fine-tuning for:
  • Customer service Automation
  • Content generation
  • Code generation and auto-completion
  • Translation
  • Text summarization
Fine-tuning has shown improved performance in areas like following instructions, consistent output formatting, and adjusting the model's tone to match a brand's voice. It also enables prompt size reduction and faster API calls. Fine-tuning is most effective when combined with other techniques like prompt engineering and information retrieval. Your training data and validation data sets consist of input and output examples for how you would like the model to perform. For chat task type, each row in the dataset should be a list of JSON objects. Each row corresponds to a conversation and each object in the row is a turn/utterance in the conversation. Learn more at https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/models

Quick facts

Model provider
TypeChat completions
LifecycleGenerally available (GA)