babbage-002
Version: 718166
This model can be deployed for both inference and fine-tuning purposes.
Model family: GPT-3
Babbage-002 is the latest versions of Babbage, GPT3 base models. Babbage-002 replaces the deprecated Ada and Babbage models. It is a smaller, faster model that is primarily used for fine tuning tasks.
This model supports 16384 max input tokens and training data is up to Sep 2021.
Bababge-002 now supports fine-tuning, allowing developers and businesses to customize the model for specific applications.
Your training data and validation data sets consist of input and output examples for how you would like the model to perform. The training and validation data you use must be formatted as a JSON Lines (JSONL) document in which each line represents a single prompt-completion pair.
Learn more at https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/models
Model Specifications
Last UpdatedOctober 2023
Provider