In IBM watsonx.ai, you can use IBM foundation models that are built with integrity and designed for business.
The following families of IBM foundation models are available in watsonx.ai:
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 that are 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:
- granite-7b-lab
- granite-13b-chat-v2
- granite-13b-instruct-v2
- granite-8b-japanese
- granite-20b-multilingual
- granite-3b-code-instruct
- granite-8b-code-instruct
- granite-20b-code-instruct
- granite-34b-code-instruct
- granite-3-2b-instruct
- granite-3-8b-instruct
- granite-guardian-3-2b
- granite-guardian-3-8b
- granite-ttm-512-96-r2
- granite-ttm-1024-96-r2
- granite-ttm-1536-96-r2
The following sections provide a short description and a few resources for learning about each model. For more information, see Supported foundation models.
granite-7b-lab
General use model that is built with a novel alignment tuning method from IBM Research. Large-scale Alignment for chatBots, or LAB is a method for adding new skills to existing foundation models by generating synthetic data for the skills, and then using that data to tune the foundation model.
For prompting guidelines, see Prompting the granite-7b-lab foundation model from IBM.
For model specs, see Supported foundation models.
Model card: granite-7b-lab model card
Try it out:
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.
For prompting guidelines, see Prompting the granite-13b-chat-v2 foundation model from IBM.
For model specs, see Supported foundation models.
Model card: granite-13b-chat-v2 model card
Try it out:
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.
For model specs, see Supported foundation models.
Model card: granite-13b-instruct-v2 model card
Try it out:
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.
For model specs, see Supported foundation models.
Model card: granite-8b-japanese model card
Try it out:
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.
For model specs, see Supported foundation models.
Model card: granite-20b-multilingual model card
Try it out:
Granite Code models
Instruction fine-tuned models that support code discussion, generation, and conversion. Use these foundation models for programmatic coding tasks. The Granite Code models are fine-tuned on a combination of instruction data to enhance instruction-following capabilities including logical reasoning and problem solving.
- granite-3b-code-instruct
- granite-8b-code-instruct
- granite-20b-code-instruct
- granite-34b-code-instruct
The following Granite Code foundation models are instruction-tuned versions of the granite-20b-code-base foundation model that are designed for text-to-SQL generation tasks.
- granite-20b-code-base-schema-linking
- granite-20b-code-base-sql-gen
Try them out by using the sample notebook, Inferencing with Granite Text-to-SQL Models sample notebook.
For more information, see the following topics:
Model cards:
- granite-3b-code-instruct model card
- granite-8b-code-instruct model card
- granite-20b-code-instruct model card
- 20b base schema linking model card
- 20b base SQL gen model card
- granite-34b-code-instruct model card
Try them out:
Granite Instruct models
Lightweight and open-source third generation Granite models that are fine tuned on a combination of permissively licensed open-source and proprietary instruction data. The Granite Instruct language models designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, funcion-calling, and more.
- granite-3-2b-instruct
- granite-3-8b-instruct
The Granite Instruct 3.1 foundation models support 116 programming languages. For more information, see the following topics:
- Supported foundation models
- Prompt anatomy for Granite 3.0 models
- Prompt examples
- Tool-calling sample
- Code recipes
Model cards:
Try them out:
Granite Guardian models
Granite Guardian models are fine tuned third generation Granite Instruct models trained on unique data comprising human annotations and synthetic data. The foundation models are useful for risk detection use cases which are applicable across a wide-range of enterprise applications.
- granite-guardian-3-2b
- granite-guardian-3-8b
For more information, see the following topics:
Model cards:
Try them out:
Granite time series models
IBM Granite time series foundation models are compact pre-trained models for multivariate time-series forecasting from IBM Research, also known as Tiny Time Mixers (TTM).
The Granite time series models were trained on almost a billion samples of time series data from various domains, including electricity, traffic, manufacturing, and more. You can apply one of these pre-trained models on your target data to get an initial forecast without having to train the model on your data. When given a set of historic, timed data observations, the Granite time series foundation models can apply their understanding of dynamic systems to forecast future data values.
The following time series foundation models are available for use in watsonx.ai:
granite-ttm-512-96-r2: Requires at least 512 data points per dataset.granite-ttm-1024-96-r2: Requires at least 1,024 data points per dataset.granite-ttm-1536-96-r2: Requires at least 1,536 data points per dataset.
The Granite time series models work best with data points in minute or hour intervals and generate a forecast dataset with up to 96 data points per time series, per target column.
Try them out:
- You can submit a zero-shot inferencing request to the models by using the time series forecast method of the watsonx.ai API. For more information, see Use the IBM Granite time series models and forecast API to forecast trends.
- Sample notebook: Use Time Series Foundation Models and timeseries data to predict energy demand
Learn more
Slate foundation models
The Slate family of IBM foundation models includes encoder-only models that specialize in natural language processing and text embedding tasks.
The following Slate embedding models are available in watsonx.ai today:
- slate-125m-english-rtrvr-v2, slate-125m-english-rtrvr
- 768-dimension embedding models that convert text into text embeddings.
- slate-30m-english-rtrvr-v2, slate-30m-english-rtrvr
- 384-dimension embedding models that convert text into text embeddings.
For more information about these models, see Supported encoder foundation models.
For more information about using Slate models to convert sentences and passages into text embeddings, see Text embedding generation.
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