Tag: LLM

Apple publishes MLX – an array framework for machine learning on Apple silicon, brought to you by Apple machine learning research.

Some key features of MLX include:

• Familiar APIs: MLX has a Python API that closely follows NumPy. MLX also has a fully featured C++ API, which closely mirrors the Python API. MLX has higher-level packages like mlx.nn and mlx.optimizers with APIs that closely follow PyTorch to simplify building more complex models.
• Composable function transformations: MLX has composable function transformations for automatic differentiation, automatic vectorization, and computation graph optimization.
• Lazy computation: Computations in MLX are lazy. Arrays are only materialized when needed.
• Dynamic graph construction: Computation graphs in MLX are built dynamically. Changing the shapes of function arguments does not trigger slow compilations, and debugging is simple and intuitive.
• Multi-device: Operations can run on any of the supported devices (currently, the CPU and GPU).
• Unified memory: A notable difference from MLX and other frameworks is the unified memory model. Arrays in MLX live in shared memory. Operations on MLX arrays can be performed on any of the supported device types without moving data.

MLX

Framework is available under MIT license and comes with examples on various machine learning tasks.

GitHub: mlx

Small list for this weekend, so – more time to unwind. Let's go.

• Keith Harrison explores SwiftData fetch options – SwiftData Fetching An Existing Object;
  
  
• Learn how to utilize the Scan and Reduce operators in SwiftUI with Combine by Leonardo Maia Pugliese covers differences between scan and reduce in Combine;
  
  
• Natascha Fadeeva explains how observation works with new @Observable macro – How to manually subscribe to changes of SwiftUI's @Observable objects;
  
  
• Apple recently announced that developers will need to declare reasons to use some of the APIs – How to check if you use a required reason API by Marco Eidinger will help you to prepare for this;
  
  
• Antoine van der Lee helps you to prepare to migrate to Swift 6 – Swift 6: Preparing your Xcode projects for the future;
  
  
• The Future is Now: Integrating AI in Software Development  by Beau Nouvelle explores capabilities that AI could bring to your apps;
  
  
• Majid Jabrayilov continues his saga on StoreKit 2 – Mastering StoreKit 2. SubscriptionStoreView in SwiftUI;
  
  
• And another hot take on subscriptions by Charlie Chapman – How to use StoreKit views to build a subscription app paywall with SwiftUI;
  
  
• Peter Meinertzhagen talks about good onboarding experiences – Why your onboarding experience might be too short;
  
  
• Invisible Details of Interaction Design by Rauno Freiberg goes through big and small details of interactions in Apple platforms.

That is it for today. Have a great weekend and come back next Friday for another pack of great reads!

Hugging Face releases Swift Transformers – package to implement transformers APIs in Swift.

Overall, couple of products were released and updated:

• swift-transformers, an in-development Swift package to implement a transformers-like API in Swift focused on text generation. It is an evolution of swift-coreml-transformers with broader goals: Hub integration, arbitrary tokenizer support, and pluggable models.
• swift-chat, a simple app demonstrating how to use the package.
• An updated version of exporters, a Core ML conversion package for transformers models.
• An updated version of transformers-to-coreml, a no-code Core ML conversion tool built on exporters.
• Some converted models, such as Llama 2 7B or Falcon 7B, ready for use with these text generation tools.

Package currently supports following models:

• Llama 2;
• Falcon;
• StarCoder models, based on a variant of the GPT architecture;
• GPT family, including GPT2, distilgpt, GPT-NeoX, GPT-J.

As of now package is in active development. It is not expected to be used in production projects without appropriate testing.

GitHub:

• swift-transformers (Apache License 2.0)
• swift-chat
• exporters

Hugging Face: Releasing Swift Transformers: Run On-Device LLMs in Apple Devices