Databricks · Chat
DBRX-instruct
- llminfo IQ
- 96.9
- Market median price
- $1.20 blended / 1M
- Max context
- 33K
- Listings
- 3
Evidence and sources
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Trade-offs
Fewer provider choices
Among the weaker models in its class
Input & output
as stated by the model's providersBenchmarks
Named effort levels run from lowest to highest. Select a result to see its source details.
Safety
| Benchmark | Score |
|---|---|
| Safety: BBQ - BBQ accuracy | |
| AIR-Bench: AIRBench 2024 - #1: Confidentiality | |
| AIR-Bench: AIRBench 2024 - #2: Integrity | |
| AIR-Bench: AIRBench 2024 - #3: Availability |
Show 62 more benchmarksHide 62 benchmarks
Knowledge
Show 53 more resultsHide 53 results
Long context
| Benchmark | DBRX · · 36B/132B · |
|---|---|
| 4K | |
| 8K | |
| 16K | |
| 32K |
Show 5 more benchmarksHide 5 benchmarks
| Benchmark | DBRX · · 36B/132B · |
|---|---|
| 64K | |
| 128K | |
| Avg | |
| wAvg (dec) | |
| wAvg (inc) |
Reasoning
Coding
Math
Science
General
Factuality
Instruction following
Multilingual
Speech
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · Stanford HELM (Stanford CRFM), Apache-2.0 (licence) · EvalPlus Leaderboard and EvalPerf (evalplus.github.io), Apache-2.0; EvalPerf win-rate fractions converted to percentages (licence) · NVIDIA RULER, Hsieh et al. Official README numeric table; no separate results licence asserted.
Around the web
- Databricks Launches DBRX, A New Standard for Efficient Open Source Models - Databricks
March 27, 2024 Databricks Launches DBRX, A New Standard for Efficient Open Source Models DBRX …
March 27, 2024 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 …databricks.com
- Introducing DBRX: A New State-of-the-Art Open LLM | Databricks Blog
outperforms established open source models on language understanding (MMLU), Programming (HumanEval), and Math (GSM8K). The …
outperforms established open source models on language understanding (MMLU), Programming (HumanEval), and Math (GSM8K). The weights of the base model ( DBRX Base ) and the finetuned model ( DBRX Inst…databricks.com
- Announcing DBRX: A new standard for efficient open source LLMs | Databricks Blog
Towards that, we designed DBRX to be easily customizable so that enterprises can improve the …
Towards that, we designed DBRX to be easily customizable so that enterprises can improve the quality of their AI applications. Starting today on the Databricks Platform, enterprises can interact with…databricks.com
- Meet DBRX, the New Standard for High-Quality LLMs | Databricks
open source foundation model that sets the standard for quality and efficiency. With up to …
open source foundation model that sets the standard for quality and efficiency. With up to 3x faster inference, DBRX outperforms all other open models in quality benchmarks — and that allows you to q…databricks.com
- DBRX: A New Standard for Open Source LLMs | Databricks
DBRX sets a new standard for efficient LLMs. It outperforms all existing open source models …
DBRX sets a new standard for efficient LLMs. It outperforms all existing open source models as well as GPT 3.5 on standard benchmarks. DBRX plus Databricks helps developers deploy production-quality …databricks.com
- Discover DBRx: Revolutionizing High-Quality LLMs for AI | Databricks
If you’re using off-the-shelf LLMs to build GenAI applications, you’re probably struggling with quality, privacy …
If you’re using off-the-shelf LLMs to build GenAI applications, you’re probably struggling with quality, privacy and governance issues. What you need is a way to cost-effectively build a custom LLM t…databricks.com
- Building DBRX-class Custom LLMs with Databricks Training | Databricks Blog
by Anna Pfohl , Cheng Li , Mihir Patel , Wai Wu , Will Gleich …
by Anna Pfohl , Cheng Li , Mihir Patel , Wai Wu , Will Gleich , Ajay Saini and Hagay Lupesko We recently introduced DBRX : an open, state-of-the-art, general-purpose LLM. DBRX was trained, fine-tuned…databricks.com
- Accelerated DBRX Inference on Databricks Model Serving | Databricks Blog
In this blog post we dive into inference with DBRX, the open state-of-the-art large language …
In this blog post we dive into inference with DBRX, the open state-of-the-art large language model (LLM) created by Databricks (see Introducing DBRX ). We discuss how DBRX was designed from the groun…databricks.com
- DBRX Models - Databricks Marketplace
Product details DBRX Instruct can be deployed directly to Databricks Model Serving for immediate use, …
Product details DBRX Instruct can be deployed directly to Databricks Model Serving for immediate use, or loaded for fine-tuning or batch inference use cases. DBRX Base can be used for further fine-tu…marketplace.databricks.com
- Databricks Launches DBRX, A New Standard for Efficient Open Source Models
for all enterprises. A recent survey from Andreessen Horowitz found that nearly 60 percent of …
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…prnewswire.com
Also known as: databricks/dbrx-instruct, fireworks_ai/accounts/fireworks/models/dbrx-instruct, nvidia_nim/databricks/dbrx-instruct
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works