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

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.

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

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.)

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

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.

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

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.

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.

Source: Databricks