PaLM 2 Text Bison
Designed for single-turn instruction tasks like classification, extraction, summarization and generation.text-bison is the name of the PaLM 2 Text Bison large language model that understands and generates language. It's a foundation model that performs well at a variety of natural language tasks such as sentiment analysis, entity extraction, and content creation. The type of content that text-bison can create includes document summaries, answers to questions, and labels that classify content.
This model card also contains text-unicorn, the largest model in the PaLM family. Unicorn models excel at complex tasks, such as coding and chain-of-thought (CoT), due to the extensive knowledge embedded into the model and its reasoning capabilities.
The PaLM 2 Text Bison is ideal for tasks that can be completed with one API response, without the need for continuous conversation. For text tasks that require back-and-forth interactions, use the PaLM 2 Chat Bison.
You can use Vertex AI Studio to experiment with the text-bison model in the Google Cloud console. The text-bison model also supports Python.
To use the PaLM 2 Text Bison in the Google Cloud console, open it in Vertex AI Studio. To use it programmatically, you need to set it up in Python. Use the following topics to get started:
To use the text-bison model in Vertex AI Studio, click Open Prompt Design on this page. In Vertex AI Studio, you can enter a sample text prompt, then click on Submit to view the output generated by PaLM 2 Text Bison.
To use the text-bison model with the command line interface (CLI), do the following:
Install the Google Cloud SDK if you haven't already or open Cloud Shell and skip to step 3.
Obtain authentication credentials. Create local credentials by running the following command and following the oauth2 flow (read more about the command here:
Read more about Google Cloud Platform Authentication.
In the following code sample, replace PROJECT_ID
with your Google Cloud project ID and then enter the following, which prompts the model to provide ten interview questions for the role of a program manager:
To use the text-bison model with Python, do one of the following:
Option 1: Vertex AI SDK for Python
Option 2: Vertex AI Python SDK with Google Colab
Use the following to request a model response with a Google Colaboratory (Google Colab) notebook.
Install Python 3.7 or higher if it's not already installed.
Set up the Vertex AI SDK for Python. After installing you'll be prompted to restart your Colab notebook runtime.
Use the following code in your notebook to request a model response, replacing PROJECT_ID
with your Google Cloud project ID:
Resource ID | Release date | Release stage | Description |
---|---|---|---|
text-bison@002 | 2023-12-04 | General Availability | Updated version with enhanced quality |
text-bison-32k@002 | 2023-12-04 | General Availability | Updated version with enhanced quality |
text-unicorn@001 | 2023-11-30 | General Availability | |
text-bison | 2023-08-29 | General Availability | |
text-bison-32k | 2024-04-01 | General Availability | |
text-bison@001 | 2023-06-07 | General Availability | |
text-bison@001 | 2024-04-01 | General Availability | Quality improvements and restage -001 as the first stable base model release |
Google Cloud Console has failed to load JavaScript sources from www.gstatic.com.
Possible reasons are: