Article complete

Apple Open Sources DCLM-Baseline 7B, Outperforms Meta’s Llama 2

The new model integrates data from DCLM-BASELINE, StarCoder, and ProofPile2, achieving an MMLU score of 0.6372, placing it between Mistral and Llama3 in performance metrics.

Apple logo illuminated in a forest setting at dusk, surrounded by trees and a serene atmosphere.

Key takeaways

  • Apple releases open-source DCLM-Baseline 7B, a powerful LLM with 7 billion parameters.
  • Achieves an MMLU score of 0.6372, outperforming Meta's Llama 2 and matching Mistral.
  • Integrates data from DCLM-BASELINE, StarCoder, and ProofPile2, trained on 2.5 trillion tokens.
  • Available under Apple Sample Code License on Hugging Face and Transformers for developers.
  • Supports enhanced AI capabilities for Siri, developed using Apple’s AXLearn framework.

Takeaways drafted with AI from the article text.

https://twitter.com/_philschmid/status/1814274909775995087?s=12

The new model integrates data from DCLM-BASELINE, StarCoder, and ProofPile2, achieving an MMLU score of 0.6372, placing it between Mistral and Llama3 in performance metrics. It is licensed under the Apple Sample Code License and is available on Hugging Face and in Transformers. The model is trained using PyTorch with the OpenLM framework, matching the performance of closed-dataset models like Mistral.

This comes after Apple at WWDC 2024 introduced Apple Intelligence to enhance Siri’s capabilities with generative AI. For the same Apple built a 3 billion parameter on-device language model and a larger server-based model accessible via Private Cloud Compute on Apple silicon servers. These models were developed using Apple’s AXLearn framework, an open-source project based on JAX and XLA.

Earlier this Apple has also open sourced MM1 series, featuring multimodal AI models with 30 billion parameters, and ReALM, which combines text and images to improve interaction. 

The company had also released  ‘Ferret-UI,’ a multimodal AI model designed for precise task execution concerning user interfaces and handling open-ended language instructions. The core focus of Ferret-UI lies in its multimodal capabilities, combining advanced language understanding with visual comprehension tailored specifically for mobile UI screens, incorporating referring, grounding, and reasoning capabilities. 

Published Updated

Spotted an error? Tell our editors. Read our editorial standards and corrections.

More in this story

Open Source AI · 4 stories
  1. Apple Open Sources MLX, Machine Learning Framework for Apple Silicon
  2. Apple Releases Four Open Source LLMs with OpenELM Series of Models
  3. You are here: Apple Open Sources DCLM-Baseline 7B, Outperforms Meta’s Llama 2
  4. Perplexity Releases Advanced Deep Research Upgrade, Open-Sources DRACO Benchmark
About the author

Tech Journalist

Siddharth is a media graduate who loves to explore tech through journalism and putting forward ideas worth pondering about in the era of artificial intelligence.

All stories
Belamy · Daily

The day’s AI news, before your first meeting.