State-of-the-art transformers, brick by brick. Curated Transformers is a transformer library for PyTorch. It provides state-of-the-art models that are composed of a set of reusable components. Supports state-of-the-art transformer models, including LLMs such as Falcon, Llama, and Dolly v2. Implementing a feature or bugfix benefits all models. For example, all models support 4/8-bit inference through the bitsandbytes library and each model can use the PyTorch meta device to avoid unnecessary allocations and initialization.

Features

  • Each model is composed from a set of reusable building blocks, providing many benefits
  • Consistent type annotations of all public APIs
  • Integrates well with your existing type-checked code
  • Great for education, because the building blocks are easy to study
  • Minimal dependencies
  • Adding new models to the library is low-effort

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow Curated Transformers

Curated Transformers Web Site

Other Useful Business Software
Cut Cloud Costs with Google Compute Engine Icon
Cut Cloud Costs with Google Compute Engine

Save up to 91% with Spot VMs and get automatic sustained-use discounts. One free VM per month, plus $300 in credits.

Save on compute costs with Compute Engine. Reduce your batch jobs and workload bill 60-91% with Spot VMs. Compute Engine's committed use offers customers up to 70% savings through sustained use discounts. Plus, you get one free e2-micro VM monthly and $300 credit to start.
Try Compute Engine
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Curated Transformers!

Additional Project Details

Programming Language

Python

Related Categories

Python Large Language Models (LLM), Python LLM Inference Tool

Registered

2023-08-25