Easy-to-use headless React Hooks to run LLMs in the browser with WebGPU. As simple as useLLM().

Features

  • Supports Vicuna 7B
  • Use custom system prompts and "user:"/"assistant:" role names
  • Completion options like max tokens and stop sequences
  • No data leaves the browser. Accelerated via WebGPU
  • Hooks built to 'Bring your own UI'
  • Persistent storage for conversations in browser storage. Hooks for loading and saving conversations

Project Samples

react-llm Screenshot 1

Project Activity

See All Activity >

Categories

Large Language Models (LLM), Headless Browsers

License

MIT License

Follow react-llm

react-llm Web Site

Other Useful Business Software
Error to trace to log to deploy. One click. No SSH. Icon
Error to trace to log to deploy. One click. No SSH.

Catch the cause before the pager goes off.

AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
Free 30 days.
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of react-llm!

Additional Project Details

Programming Language

TypeScript

Related Categories

TypeScript Large Language Models (LLM), TypeScript Headless Browsers

Registered

2023-08-25
Report inappropriate content