Democratizing Large Language Model Development with InstructLab Support in WatsonX.AI
The advent of generative AI is revolutionizing industries worldwide, automating and enhancing creative and analytical processes. According to McKinsey, generative AI has the potential to add $4 trillion to the global economy. However, only 10% of companies have successfully put their generative AI solutions into production, highlighting the need for a more efficient and scalable approach to language model development.
The Next Iteration of Language Models
Scaling AI requires significant investment in talent, infrastructure, and data. The quality of datasets used to train large language models (LLMs) is crucial, and companies are looking to adapt and tune models with their proprietary data to teach the model the language of their business. Model architectures are becoming increasingly modular, relying on external memory, and organizations are taking a multimodel approach to work with various models, whether open-source or commercial, depending on the use case.
Governance is critical, and models must be governed and monitored for trust, transparency, and end-to-end explainability, including tracking models for hallucinations, bias, drift, and more. The emergence of AI agents as the main experience layer for how consumers interact and chat with generative AI applications is also on the rise.
Overcoming the Challenges of LLM Development
The lack of standards and community-driven development in LLMs has led to the creation of multiple forks or variants of an LLM, catering to different specializations. This has resulted in monolithic development with siloed contributions, where no one knows what’s coming or how to best train and tune the model for their desired task.
Introducing InstructLab: Disrupting Model Customization
To overcome these challenges, IBM Research released a new methodology called LAB (Large-Scale Alignment for ChatBots), which aims to overcome some challenges around LLM training by using taxonomy-guided synthetic data generation. InstructLab, an open-source project by IBM Research and Red Hat, builds on the LAB technique for a community-driven approach to language model development through skills and knowledge training.
InstructLab offers a novel method for collaborative customization and tuning of LLMs. The toolkit systematically generates synthetic data for tasks that you want chatbots to accomplish, and for assimilating new knowledge and capabilities into the foundation model—without overwriting what the model has already learned.
InstructLab Architecture
Our New LAB-Aligned Models Achieve State-of-the-Art Chat Performance
Based on internal benchmark testing, we’ve seen great performance with the InstructLab technique on the MT-Bench score for IBM’s Granite-chat-13B-v2 model in WatsonX.AI. IBM Research also found that when applying the InstructLab method to the open-source LLM Merlinite, which is built on Mistral 7B, it achieved strong scores on MT-Bench and MMLU (5-shot).
Developers can access a series of InstructLab-tuned language models and open code models through WatsonX.AI. This includes the release of four InstructLab-trained language models (granite-7b-lab, merlinite-7b, granite-20b-multilingual, and granite-13b-chat-v2) in addition to four state-of-the-art open code models (granite-3b, granite-8b, granite-20b, and granite-34b) that perform well across a range of coding tasks, including code generation and fixing.
Through the InstructLab project, IBM and Red Hat have released select open-source licensed Granite language and code models under the Apache 2.0 license. Through subscribing to the commercial license of RHEL AI from Red Hat or by accessing the InstructLab models and toolkit in WatsonX.AI, clients can get access to these open-source-licensed Granite language and code models that are also supported and indemnified by Red Hat.
 Taxonomy Explorer
Providing a Platform for Collaborative Language Model Enhancements
We’re continuously evolving our model strategy in WatsonX.AI to help enterprise developers and line-of-business (LoB) leaders accelerate AI application development. This requires a full-stack approach for the open-hybrid cloud to scale generative AI capabilities, tools, and platforms, to succeed in the rapidly evolving digital landscape.
In WatsonX.AI, we’ve built an intuitive, collaborative development studio environment with prebuilt generative AI patterns, while integrating essential enterprise features for production-level workloads. Enterprise developers can optimize the development of production-ready AI applications with models, tools, SDKs, Notebooks, API integrations, and runtimes to deploy AI applications at scale.
At IBM, we are committed to fostering an open innovation ecosystem around AI to help our clients maximize model flexibility and enhancements with new skills and knowledge. As part of our hybrid, multimodel strategy, we’ll continue to offer a mix of third-party models from strategic partners, such as Meta and Mistral AI, as well as select open-source models from Hugging Face, bring-your-own models (BYOM), in addition to proprietary, domain-specific IBM-developed models with IP indemnification, as well as IBM open-sourced InstructLab code and language models licensed from Red Hat.
Our open, multimodel, multilingual strategy is continuing to take shape as highlighted in our most recent strategic collaboration with the Spanish government that aims to build the world’s leading suite of foundation models, including both large language models and small language models, proficient in the Spanish language and co-official languages.
Through our close partnership with Red Hat, in the future, we intend to embed the supported InstructLab alignment CLI from RHEL AI’s foundation model runtime engine directly in WatsonX.AI to support end-to-end developer AI workflows to quickly adapt models with new skills and knowledge using proprietary business data, all within a single studio interface. This might help facilitate faster deployment, tuning, and customization of open and custom InstructLab-trained models in WatsonX.AI to then scale those models across machines, devices, end-applications, and business processes.
Further, organizations might benefit from native integrations to the rest of the WatsonX platform, to build, scale, and govern their AI solutions with data lineage, storage, and lifecycle governance—across any cloud or on-premises environment.
Ready to Learn More?
To learn more about the InstructLab project from IBM Research and Red Hat, visit the GitHub page and get started contributing to the community.
Book a meeting if you’re interested in knowing more about WatsonX.AI—IBM’s next-generation enterprise studio for AI builders to train, validate, tune, and deploy AI models—or begin working with the InstructLab-trained language and code models and other foundation models in our library, by signing up for a free trial of WatsonX.AI.
