Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Description

Uncover and rely on data for your analyses and models while enhancing productivity by dismantling silos. Gain instant insights into data usage by others and locate data within your organization effortlessly through a straightforward text search. Utilizing a PageRank-inspired algorithm, the system suggests results based on names, descriptions, tags, and user activity associated with tables or dashboards. Foster confidence in your data with automated and curated metadata that includes detailed information on tables and columns, highlights frequent users, indicates the last update, provides statistics, and offers data previews when authorized. Streamline the process by linking the ETL jobs and the code that generated the data, making it easier to manage table and column descriptions while minimizing confusion about which tables to utilize and their contents. Additionally, observe which data sets are commonly accessed, owned, or marked by your colleagues, and discover the most frequent queries for any table by reviewing the dashboards that leverage that specific data. This comprehensive approach not only enhances collaboration but also drives informed decision-making across teams.

Description

TabFM is an innovative zero-shot foundation model specifically created for handling tabular data, aimed at streamlining classification and regression processes that usually necessitate extensive manual model training, hyperparameter optimization, and tailored feature engineering. By transforming the challenge of tabular prediction into an in-context learning task, TabFM avoids the need to train a new supervised model for every dataset; instead, it consolidates historical training examples and target testing rows into a single cohesive prompt, allowing it to discern the intricate relationships between various columns and rows during inference. Given that tables are inherently two-dimensional and do not rely on a specific order, TabFM employs a hybrid architecture that integrates alternating attention mechanisms for both rows and columns, row compression techniques, and a specialized Transformer designed for in-context learning based on these compressed row embeddings. This sophisticated framework enables the model to effectively capture complex interactions and dependencies among features while maintaining computational efficiency, particularly advantageous for processing larger datasets. Furthermore, this approach not only enhances performance but also significantly reduces the time and resources typically required for model development in tabular data tasks.

API Access

Has API No 

API Access

Has API No 

Screenshots View All

Screenshots View All

Integrations

AWS Glue Yes 
Amazon Athena Yes 
Amazon Redshift Yes 
Amazon Web Services (AWS) Yes 
Apache Cassandra Yes 
Apache Druid Yes 
Apache Hive Yes 
Apache Spark Yes 
Datafold Yes 
Delta Lake Yes 
Elasticsearch Yes 
Google Cloud BigQuery Yes 
IBM Db2 Yes 
MySQL Yes 
OpenMetadata Yes 
Oracle Cloud Infrastructure Yes 
PostgreSQL Yes 
SQL Server Yes 
Snowflake Yes 
Vertica Yes 

Integrations

AWS Glue No 
Amazon Athena No 
Amazon Redshift No 
Amazon Web Services (AWS) No 
Apache Cassandra No 
Apache Druid No 
Apache Hive No 
Apache Spark No 
Datafold No 
Delta Lake No 
Elasticsearch No 
Google Cloud BigQuery No 
IBM Db2 No 
MySQL No 
OpenMetadata No 
Oracle Cloud Infrastructure No 
PostgreSQL No 
SQL Server No 
Snowflake No 
Vertica No 

Pricing Details

No price information available.
Free Trial No 
Free Version No 

Pricing Details

Free
Free Trial No 
Free Version Yes 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support Yes 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support Yes 

Types of Training

Training Docs Yes 
Webinars Yes 
Live Training (Online) No 
In Person No 

Types of Training

Training Docs Yes 
Webinars No 
Live Training (Online) No 
In Person No 

Vendor Details

Company Name

Amundsen

Country

United States

Website

www.amundsen.io

Vendor Details

Company Name

Google

Founded

1998

Country

United States

Website

research.google/blog/introducing-tabfm-a-zero-shot-foundation-model-for-tabular-data/

Product Features

Product Features

Alternatives

Alternatives

Evo 2 Reviews

Evo 2

Arc Institute
TabPFN-3.5 Reviews

TabPFN-3.5

Prior Labs