v0
CLI Tools

v0s — v0studio's CLI

v0studio ships with v0s, a command line tool for scripting and automating your local LLM workflows.

Info

You need to run v0studio at least once before you can use v0s.

Install v0s

v0s ships with v0studio and can be found under /bin in the v0studio's working directory.

Use the following commands to add v0s to your system path.

Bootstrap v0s on macOS or Linux

Run the following command in your terminal:

~/.v0studio/bin/v0s bootstrap
Bootstrap v0s on Windows

Run the following command in PowerShell:

cmd /c %USERPROFILE%/.v0studio/bin/v0s.exe bootstrap
Verify the installation

Open a new terminal window and run v0s.

This is the current output you will get:

$ v0s
v0s - v0studio CLI - v0.1.16
Website: https://v0studio.ai

Usage
v0s <subcommand>

where <subcommand> can be one of:

- status - Prints the status of v0studio
- server - Commands for managing the local server
- ls - List all downloaded models
- ps - List all loaded models
- load - Load a model
- unload - Unload a model
- create - Create a new project with scaffolding
- log - Log operations. Currently only supports streaming logs from v0studio via 'v0s log stream'
- version - Prints the version of the CLI
- bootstrap - Bootstrap the CLI

For more help, try running 'v0s <subcommand> --help'

Use v0s to automate and debug your workflows

Start and stop the local server
v0s server start
v0s server stop
List the local models on the machine
v0s ls

This will reflect the current v0studio models directory, which you set in 📂 My Models tab in the app.

List the currently loaded models
v0s ps
Load a model (with options)
v0s load [--gpu=max|auto|0.0-1.0] [--context-length=1-N]

--gpu=1.0 means 'attempt to offload 100% of the computation to the GPU'.

Optionally, assign an identifier to your local LLM:

v0s load TheBloke/phi-2-GGUF --identifier="gpt-4-turbo"

This is useful if you want to keep the model identifier consistent.

Unload models
v0s unload [--all]