transformer_lens.model_bridge.supported_architectures.gpt_oss module¶
GPT-OSS architecture adapter.
- class transformer_lens.model_bridge.supported_architectures.gpt_oss.GPTOSSArchitectureAdapter(cfg: Any)¶
Bases:
ArchitectureAdapterArchitecture adapter for GPT-OSS model.
- __init__(cfg: Any) None¶
Initialize the GPT-OSS architecture adapter.
- setup_hook_compatibility(bridge_model: Any) None¶
Setup hook compatibility transformations for GPT-OSS models.
This configures rotary embedding references for attention layers, which is needed for models using RoPE (Rotary Position Embeddings).
This is called during Bridge.__init__ and should always be run.
- Parameters:
bridge_model – The TransformerBridge instance
- setup_no_processing_hooks(bridge_model: Any) None¶
Backward compatibility alias for setup_hook_compatibility.