Note

This model has special pricing. Check out here

Overview

Even as PaLM 2 is more capable, it’s also faster and more efficient than previous models — and it comes in a variety of sizes, which makes it easy to deploy for a wide range of use cases. PaLM 2 is available in four sizes, from smallest to largest: Gecko, Otter, Bison, and Unicorn. Gecko is so lightweight that it can work on mobile devices and is fast enough for great interactive applications on-device, even when offline. This versatility means PaLM 2 can be fine-tuned to support entire classes of products in more ways, to help more people. Bison: The best value in terms of capability and cost.

Text-bison

Text-bison is the name of the PaLM 2 for text 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.

Use cases

• Classification

Prompt: Categorizing news articles into different topics.
a) “Breaking News: Stock markets experience a sharp decline amid fears of an economic downturn.”
b) “Sports Update: The national football team secured a thrilling victory in the championship finals.”
c) "Technology: The latest smartphone model boasts innovative features and improved performance."

Response: a) Business b) Sports c) Technology

• Question answering

Prompt: Who was the first person to walk on the moon

Response: Neil Armstrong was the first person to walk on the moon. He stepped onto the lunar surface at 10:56 p.m. EST on July 20, 1969, becoming the first human to do so. Armstrong was joined by fellow astronaut Buzz Aldrin on the Apollo 11 mission, which was the first manned mission to land on the moon.

• Summarization:

Prompt: Summarize this,
Jupiter is the fifth planet from the Sun and the largest in the Solar System. It is a gas giant with a mass one-thousandth that of the Sun, but two-and-a-half times that of all the other planets in the Solar System combined. Jupiter is one of the brightest objects visible to the naked eye in the night sky, and has been known to ancient civilizations since before recorded history. It is named after the Roman god Jupiter.[19] When viewed from Earth, Jupiter can be bright enough for its reflected light to cast visible shadows,[20] and is on average the third-brightest natural object in the night sky after the Moon and Venus.

Response: Jupiter is the fifth planet from the Sun and the largest in the Solar System. It is a gas giant with a mass one-thousandth that of the Sun, but two-and-a-half times that of all the other planets in the Solar System combined. It is one of the brightest objects visible to the naked eye in the night sky, and has been known to ancient civilizations since before recorded history.

• Sentiment analysis

Prompt: sentiment classification from customer reviews.
a) “I absolutely loved the movie! The acting was phenomenal, and the plot kept me engaged throughout.”
b) “The customer service was terrible. I had a frustrating experience dealing with their support team.”
c) “This product is just average. It does the job, but nothing exceptional.”

a) is positive. The writer uses words like "absolutely loved" and "phenomenal" to express their positive opinion of the movie.
b) is negative. The writer uses words like "terrible" and "frustrating" to express their negative opinion of the customer service.
c) is neutral. The writer uses words like "just average" and "does the job" to express their neutral opinion of the product.

• Entity extraction

Prompt: Identifying and extracting specific entities (e.g., names, locations, dates) from text.:
"John Doe, a renowned scientist from New York, will be presenting his research at the conference on July 25th

Response: The entities in the text are: - John Doe: a person - New York: a location - July 25th: a date - conference: an event

Prompt: Identifying and extracting specific entities (e.g., names, locations, dates) from text.
"The company announced the opening of its new headquarters in London, United Kingdom."

Response: London is a city. It is the location of the headquarters. United Kingdom is a country. It is the country of the location.

Disclaimer

Please be advised that this model utilizes wrapped Artificial Intelligence (AI) provided by GCP (the "Vendor"). These AI models may collect, process, and store data as part of their operations. By using our website and accessing these AI models, you hereby consent to the data practices of the Vendor. We do not have control over the data collection, processing, and storage practices of the Vendor. Therefore, we cannot be held responsible or liable for any data handling practices, data loss, or breaches that may occur. It is your responsibility to review the privacy policies and terms of service of the Vendor to understand their data practices. You can access the Vendor's privacy policy and terms of service at https://cloud.google.com/privacy.

We disclaim all liability with respect to the actions or omissions of the Vendor, and we encourage you to exercise caution and to ensure that you are comfortable with these practices before utilizing the AI models hosted on our site.