git
ask
hub
Privacy
Terms
Sign in with GitHub
codeitlikemiley/rusty_llama
↗
Language ·
Rust
License ·
MIT
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: codeitlikemiley
Ask anything about this repo to start.
I want to run a ChatGPT-like chatbot on my Mac without any cloud API calls. Help me set up rusty_llama, download a Wizard-Vicuna model file, and launch the chat interface using Apple Metal acceleration.
I have rusty_llama running but I'm on an Nvidia GPU Linux machine. Help me adjust the settings to switch from Apple Metal to CUDA acceleration so the model runs locally.
I'm learning Rust and want to understand how rusty_llama serves a full-stack web app. Walk me through how the Rust backend serves the frontend and interfaces with the local language model.
I want to try a different open-source model with rusty_llama instead of Wizard-Vicuna. Help me figure out what model formats are compatible and how to point the app to a new model file.
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).