Announced September 7, IBM’s Granite series mutli-size foundation models use the “Decoder” architecture and apply generative AI to language and code tasks. Enterprise NLP (natural language processing) tasks are supported such as summarisation, content generation, and insight extraction.
IBM plans to offer a comprehensive list of the sources of data as well as description of data processing and filtering steps performed to produce training data for the Granite series, which is due to be available this month. IBM also is offering third-party models including Meta’s Llama 2-chat 70 billon parameter model and the StarCoder LLM (large language model) for code generation on Watsonx.ai on IBM Cloud.
The Watsonx.ai models are trained on IBM’s enterprise-focused data lake. The company said it has established a training process that features rigorous data collection and leverages control points for deployments of models and applications for governance, risk assessment, compliance, and bias mitigation.
Other capabilities planned for the Watsonx platform include:
- Tuning Studio for Watsonx.ai offers a mechanism to adapt foundation models to unique downstream tasks with their own enterprise data. Tuning Studio is due this month.
- Synthetic data generator for Watsonx.ai assists users in building artificial tabular data sets from custom data schemes or internal data sets. Users will be able to extract insights for AI model training and fine-tuning with reduced risk. This capability also is due this month.
- The Watsonx.data lakehouse data store will incorporate Watsonx.ai generative AI capabilities to help users discover, visualise, and refine data through a natural language interface. This is due in preview in the fourth quarter of this year.
- Watsonx.data will integrate vector database capability to support Watsonx.ai retrieval-augmented generation use cases, also planned for a fourth quarter preview.
- Model risk governance for generative AI, launching as a tech preview for Watsonx.governance, will enable clients to explore automated collection of foundation model details and model risk governance capabilities, for viewing relevant metrics in dashboards of enterprise-wide AI workflows.
IBM also is embedding Watsonx.ai innovations across its hybrid cloud software and infrastructure, including:
- Intelligent IT automation, which enters a tech preview this week, features automation products Instana and AIOps and includes Intelligent Remediation, embedding Watsonx.ai generative AI foundation models to assist IT ops practitioners with summarisation of incident details. Prescriptive workflow suggestions will be provided to help engineers implement solutions.
- Developer services for Watsonx, to help developers bring watsonx capabilities closer to data on IBM Power for SAP workloads. SAP ABAP SDK for Watsonx will add to ways clients can use AI to inference near their data on IBM Power systems and deploy AI algorithms on sensitive data and transactions. These services are due in the first quarter of 2024.