transformer_lens.model_bridge.supported_architectures.nanogpt module

class transformer_lens.model_bridge.supported_architectures.nanogpt.NanogptArchitectureAdapter(cfg: Any)

Bases: ArchitectureAdapter

Architecture adapter for NanoGPT models.

__init__(cfg: Any) → None

Initialize the NanoGPT architecture adapter.

Parameters:

cfg – The configuration object.

convert_weights(remote_module: Any) → dict[str, Tensor]