Skip to content

Implement a base class for all models #10

@monatis

Description

@monatis

We need a base class that all the models will subclass. This class help us provide a unified interface for all the models and reduce boilerplate code.

  • Class methods that loads / deserialize weights from different formats (safetensors first, GGUF later on)
  • A method to initialize a new instance from config
  • a method to save to orbax checkpoint
  • Properties (read-only class attributes) for config values such as num_heads, head_dim etc.

Metadata

Metadata

Assignees

Labels

enhancementNew feature or request

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions