Reference - Liquid AI Docs

The LEAP Model Bundling Service is deprecated and no longer maintained. For new deployments, download GGUF files from Hugging Face and run them with llama.cpp.

All Commands

Command	Description
`leap-bundle login`	Authenticate with LEAP using API token
`leap-bundle whoami`	Show current authenticated user
`leap-bundle logout`	Logout from LEAP
`leap-bundle config`	Show current configuration
`leap-bundle validate`	Validate directory for bundle creation
`leap-bundle create`	Submit new bundle request
`leap-bundle resume`	Resume an interrupted bundle request creation
`leap-bundle list`	List all bundle requests or a specific request
`leap-bundle cancel`	Cancel a bundle request
`leap-bundle download`	Download bundle request output OR download GGUF models from a manifest URL

Global Options

All commands support these global options:

--version, -v: Show version information and exit
--help: Show help information for any command

Current Limitations

The bundle tool only works on these model types for now: LFM2, LFM2-VL, Qwen.
- We are working on expanding support to more models.

Error Handling

Authentication Errors

# Example authentication error
✗ You must be logged in. Run 'leap-bundle login' first.

# Example invalid token error
✗ Invalid API token. Please check your token and try again.

Network Errors

# Example connection error
✗ Failed to connect to server: Connection timeout

# Example API error
✗ HTTP 429 error: Rate limit exceeded. Please try again later.

File System Errors

# Example directory not found
✗ Directory does not exist: /path/to/nonexistent/directory

# Example permission error
✗ Failed to save login credentials: Permission denied

API Response Errors

The CLI tool extracts and displays error messages from API responses:

# Example API error response
✗ Bundle processing failed: Insufficient disk space on server

Exit Codes

The CLI tool uses standard exit codes:

0: Success
1: General error (authentication, network, file system, etc.)