Ai Bloks has announced the open-source launch of its development framework, llmware, for building enterprise-grade LLM-based workflow applications. They have also released the DRAGON series of 7B parameter LLMs, designed for fact-based question-answering for complex business and legal documents. The aim is to provide a unified framework, high-quality LLMs, and cost-effective private deployment options. The DRAGON models achieve high accuracy and can be seamlessly integrated with the existing BLING models for higher performance. The suite of open-source models, combined with the LLMWare development framework, offers an end-to-end solution for RAG.
LLMWare Launches RAG-Specialized 7B Parameter LLMs: Production-Grade Fine-Tuned Models for Enterprise Workflows Involving Complex Business Documents
Ai Bloks is excited to announce the release of its new development framework, LLMWare, an open-source solution for building enterprise-grade workflow applications. Today, Ai Bloks takes another big step forward with the launch of the DRAGON series of 7B parameter LLMs. These models are specifically designed for fact-based question-answering in complex business and legal documents.
The Growing Recognition of Needs
More and more enterprises are looking to deploy scalable RAG systems using their own private information. As a result, there is a growing recognition of several needs:
- A unified framework that integrates LLM models with a set of surrounding workflow capabilities
- High-quality, specialized LLMs optimized for fact-based question-answering and enterprise workflows
- Open-source, cost-effective, private deployment with flexibility and options for customization
Introducing the DRAGON Models
To meet these needs, LLMWare is launching seven DRAGON models, available in open source in its Hugging Face repository. These models have been extensively fine-tuned for RAG and built on top of leading foundation models, ensuring strong production-grade readiness for enterprise workflows.
All of the DRAGON models have been evaluated using the llmware rag-instruct-benchmark, achieving accuracy in the mid-to-high 90s on a diverse set of 100 core test questions. They are designed to avoid hallucinations and can identify when a question cannot be answered from a passage.
The DRAGON model family joins two other collections: BLING and Industry-BERT. BLING models are smaller LLM models that can run on a developer’s laptop, while DRAGON models are designed for private deployment on an enterprise-grade GPU server.
An End-to-End Solution for RAG
LLMWare provides an end-to-end solution for RAG, combining the open-source RAG-specialized models with the core development framework. It also integrates with open-source private-cloud instances of Milvus and Mongo DB. With just a few lines of code, developers can automate document ingestion and parsing, execute generative inferences, and run evidence and source verification.
According to Ai Bloks CEO Darren Oberst, LLMs enable a new automation workflow in the enterprise. LLMWare aims to bring together specialized models, data pipelines, and enabling components in a unified framework to enable enterprises to customize and deploy LLM-based automation at scale.
For more information, please visit the llmware github repository.
For direct access to the models, please visit the llmware Huggingface organization page.
Thanks to AI Bloks for their support in creating this article.
Evolve Your Company with AI
Stay competitive and leverage the benefits of LLMWare Launches RAG-Specialized 7B Parameter LLMs: Production-Grade Fine-Tuned Models for Enterprise Workflows Involving Complex Business Documents. Discover how AI can redefine your way of work by following these steps:
- Identify Automation Opportunities: Locate key customer interaction points that can benefit from AI.
- Define KPIs: Ensure your AI endeavors have measurable impacts on business outcomes.
- Select an AI Solution: Choose tools that align with your needs and provide customization.
- Implement Gradually: Start with a pilot, gather data, and expand AI usage judiciously.
For AI KPI management advice, connect with us at hello@itinai.com. For continuous insights into leveraging AI, stay tuned on our Telegram channel or follow us on Twitter.
Spotlight on a Practical AI Solution: AI Sales Bot
Consider the AI Sales Bot from itinai.com/aisalesbot. This solution is designed to automate customer engagement 24/7 and manage interactions across all customer journey stages. Discover how AI can redefine your sales processes and customer engagement. Explore solutions at itinai.com.
