Foundation models built by IBM

Granite foundation models

The Granite family of IBM foundation models includes decoder-only models that can efficiently predict and generate language.

The models were built with trusted data that has the following characteristics:

• Sourced from quality data sets in domains such as finance (SEC Filings), law (Free Law), technology (Stack Exchange), science (arXiv, DeepMind Mathematics), literature (Project Gutenberg (PG-19)), and more.
• Compliant with rigorous IBM data clearance and governance standards.
• Scrubbed of hate, abuse, and profanity, data duplication, and blocklisted URLs, among other things.

IBM is committed to building AI that is open, trusted, targeted, and empowering. For more information about contractual protections related to IBM indemnification, see the IBM Client Relationship Agreement and IBM watsonx.ai service description.

The following Granite models are available in watsonx.ai today:

granite-13b-chat-v2

General use model that is optimized for dialog use cases. This version of the model is able to generate longer, higher-quality responses with a professional tone. The model can recognize mentions of people and can detect tone and sentiment.

4.8.1 or later This model was introduced with the 4.8.1 release.

granite-13b-chat-v1

General use model that is optimized for dialog use cases. Useful for virtual agent and chat applications that engage in conversation with users.

This model is deprecated.

granite-13b-instruct-v2

General use model. This version of the model is optimized for classification, extraction, and summarization tasks. The model can recognize mentions of people and can summarize longer inputs.

4.8.1 or later This model was introduced with the 4.8.1 release.

granite-13b-instruct-v1

General use model. The model was tuned on relevant business tasks, such as detecting sentiment from earnings calls transcripts, extracting credit risk assessments, summarizing financial long-form text, and answering financial or insurance-related questions.

This model is deprecated.

granite-8b-japanese

General use model that supports the Japanese language. This version of the model is based on the Granite Instruct model and is optimized for classification, extraction, and question-answering tasks in Japanese. You can also use the model for translation between English and Japanese.

4.8.4 or later This model was introduced with the 4.8.4 release.

granite-20b-multilingual

General use model that supports the English, German, Spanish, French, and Portuguese languages. This version of the model is based on the Granite Instruct model and is optimized for classification, extraction, and question-answering tasks in multiple languages. You can also use the model for translation tasks.

4.8.4 or later This model was introduced with the 4.8.4 release.

The version 1 IBM Granite foundation models are deprecated. For more information, see Foundation model lifecycle.

Slate foundation models

The Slate family of IBM foundation models includes encoder-only models that specialize in natural language processing and text embedding tasks.

IBM Slate models power a set of libraries that you can use for common natural language processing (NLP) tasks, such as classification, entity extraction, sentiment analysis, and more.

For more information about how to use the NLP capabilities of the Slate models, see Watson NLP library.

Parent topic: Supported foundation models