Expand description
callm allows you to easily run Generative AI models (like Large Language Models) directly on your hardware, offline.
Modulesยง
- device
- This module provides computation device configuration.
- error
- This module provides custom Error type.
- loaders
- This module provides loaders for different model formats.
- models
- This module provides various model implementations for different architectures.
- pipelines
- This module provides pipelines.
- templates
- This module provides template implementations for different templating engines.
- utils
- This module provides utility functions.