Databricks Launches DBRX, A New Standard for Efficient Open Source Models

DBRX empowers organizations to build production-quality generative AI applications efficiently and gives them control over their data

SAN FRANCISCO, March 27, 2024 -- Databricks, the Data and AI company, today announced the launch of DBRX, a general purpose large language model (LLM) that outperforms all established open source models on standard benchmarks. DBRX democratizes the training and tuning of custom, high-performing LLMs for every enterprise so they no longer need to rely on a small handful of closed models. Available today, DBRX enables organizations around the world to cost-effectively build, train, and serve their own custom LLMs.

"At Databricks, our vision has always been to democratize data and AI. We're doing that by delivering data intelligence to every enterprise — helping them understand and use their private data to build their own AI systems. DBRX is the result of that aim," said Ali Ghodsi, co-founder and CEO at Databricks. "We're excited about DBRX for three key reasons: first, it beats open source models on state-of-the-art industry benchmarks. Second, it beats GPT-3.5 on most benchmarks, which should accelerate the trend we're seeing across our customer base as organizations replace proprietary models with open source models. Finally, DBRX uses a mixture-of-experts architecture, making the model extremely fast in terms of tokens per second, as well as being cost effective to serve. All in all, DBRX is setting a new standard for open source LLMs — it gives enterprises a platform to build customized reasoning capabilities based on their own data."

DBRX surpasses open source models across industry benchmarks

DBRX outperforms existing open source LLMs like Llama 2 70B and Mixtral-8x7B on standard industry benchmarks, such as language understanding, programming, math and logic. (See Figure 1.)

Figure 1: DBRX outperforms established open source models on language understanding (MMLU), Programming (HumanEval), and Math (GSM8K).

DBRX also outperforms GPT-3.5 on relevant benchmarks. (See Figure 2.)

Figure 2: DBRX outperforms GPT 3.5 across language understanding (MMLU), Programming (HumanEval), and Math (GSM8K).

For an in-depth look at model evaluations and performance benchmarks, and to see how DBRX is competitive with GPT-4 quality for internal use cases such as SQL, visit the Mosaic Research blog.

DBRX sets a new standard for efficient open source LLMs

DBRX was developed by Mosaic AI and trained on NVIDIA DGX Cloud. Databricks optimized DBRX for efficiency with a mixture-of-experts (MoE) architecture, built on the MegaBlocks open source project. The resulting model has leading performance and is up to twice as compute-efficient as other available leading LLMs.

DBRX sets a new standard for open source models, enabling customizable and transparent generative AI for all enterprises. A recent survey from Andreessen Horowitz found that nearly 60 percent of AI leaders are interested in increasing open source usage or switching when fine-tuned open source models roughly match performance of closed source models. In 2024 and beyond, enterprises expect a significant shift of usage from closed towards open source. Databricks believes DBRX will accelerate this trend.

Organizations benefit from enterprise-grade capabilities with DBRX on the Data Intelligence Platform

Paired with Databricks Mosaic AI's unified tooling, DBRX helps customers rapidly build and deploy production-quality generative AI applications that are safe, accurate, and governed without giving up control of their data and intellectual property. Customers benefit from built-in data management, governance, lineage and monitoring capabilities on the Databricks Data Intelligence Platform.

Supporting quotes

"At Accenture, we are at the forefront of implementing generative AI solutions — using advanced techniques to tailor open source models to our client's unique needs with our foundation model customization services," said Lan Guan, Chief AI Officer at Accenture. "The availability of more sophisticated open source models can provide new opportunities to drive meaningful results for our clients in every part of the enterprise."

"We're at an important inflection point for AI that requires a community of researchers, engineers and technologists to better understand it and drive meaningful innovation. This is why our team at AI2 is deeply committed to advancing the science of Generative AI through open model development and are excited to see new models like DBRX bringing greater transparency, accessibility and collaboration to the industry," said Dirk Groeneveld, Principal Software Engineer at Allen Institute for Artificial Intelligence (AI2).

"At Block, we use Generative AI tools to empower our customers and save time for Block employees through automating workflows. We look forward to exploring the capabilities of DBRX to strengthen the abilities of our AI-assisted code generation and context-driven knowledge retrieval," said Jackie Brosamer, Head of Data & ML Platform Engineering at Block.

"Databricks is a key partner to Nasdaq on some of our most important data systems. They continue to be at the forefront of the industry in managing data and leveraging AI, and we are excited about the release of DBRX. The combination of strong model performance and favorable serving economics is the kind of innovation we are looking for as we grow our use of Generative AI at Nasdaq," said Mike O'Rourke, Head of AI and Data Services at NASDAQ.

"As one of the largest technology investors in the world, Prosus recognizes the transformative power of generative AI. We're looking forward to the release of DBRX and its potential to give more enterprises the ability to build secure, portable, and highly performant customized models," said Paul van der Boor, Senior Director Data Science at Prosus Group.

"We have worked closely with the Mosaic AI team at Databricks to build customized LLMs that democratize access to coding for the next billion software developers. With the release of the powerful new DBRX open-source model, we anticipate the accelerated adoption of secure generative AI models that are customized to an organization's own data," said Michele Catasta, VP of AI at Replit.

"Our research shows enterprises plan to spend half of their AI budgets on generative AI," said Dave Menninger, Executive Director, Ventana Research, part of ISG. "One of the top three challenges they face is data security and privacy. With their end-to-end Data Intelligence Platform and the introduction of DBRX, Databricks is enabling enterprises to build generative AI applications that are governed, secure and tailored to the context of their business, while maintaining control and ownership of their IP along the way."

"Zoom has been using the power of LLMs to enable novel platform features like our AI Companion. We look forward to evaluating DBRX's potential to make training and serving custom generative AI models faster and more cost-effective for our core use cases," said Chenguang Zhu, Head of GenAI Science at Zoom.

Availability

DBRX is freely available on GitHub and Hugging Face for research and commercial use. Starting today on the Databricks Platform, enterprises can interact with DBRX, leverage its long context abilities in retrieval augmented generation (RAG) systems, and build custom DBRX models on their own unique data. DBRX is also available on AWS and Google Cloud, as well as directly on Microsoft Azure through Azure Databricks.

DBRX is also expected to be available through the NVIDIA API Catalog and supported on the NVIDIA NIM inference microservice.

To learn more about DBRX, visit the Mosaic AI research blog or join the DBRX webinar on April 25, 2024 at 8:00am PT.

About Databricks

Databricks is the Data and AI company. More than 10,000 organizations worldwide — including Comcast, Condé Nast, Grammarly, and over 50% of the Fortune 500 — rely on the Databricks Data Intelligence Platform to unify and democratize data, analytics and AI. Databricks is headquartered in San Francisco, with offices around the globe, and was founded by the original creators of Lakehouse, Apache Spark™, Delta Lake, and MLflow. To learn more, follow Databricks on LinkedIn, X and Facebook.

Press contact:

press@databricks.com