Skip to content

rope

rope

RotaryPosEncoding(d_model: int, base: int = 10000, seq_dim: int = 1, partial_rotary_factor: float = 1.0)

Unified RoPE supporting standard, Qwen, and NeoX variants.

Differences between variants are controlled by constructor args: - base: 10000 (standard/NeoX) or 1e6 (Qwen) - partial_rotary_factor: 1.0 (standard/Qwen) or <1.0 (NeoX)

NeoXRotaryPosEncoding(d_model: int, base: int = 10000, seq_dim: int = 1, partial_rotary_factor: float = 1.0)

Bases: RotaryPosEncoding

GPT-NeoX style RoPE with partial rotary dimensions.

QwenRotaryPosEncoding(d_model: int, base: int = 1000000, seq_dim: int = 1)

Bases: RotaryPosEncoding

Qwen RoPE (just RotaryPosEncoding with base=1e6).