pub struct VmfPhaseWeights {
pub thq: QTensor,
pub thk: QTensor,
pub v_proj: QTensor,
pub out_proj: QTensor,
pub decay: Vec<f64>,
pub k_gate: Option<(QTensor, Vec<f32>)>,
}Expand description
Weights of one vmf_phase layer (model.layers.{i}.vmf_attn.*).
Fields§
§thq: QTensor[nh·nphase, hidden] — query phase projection
thk: QTensor[nh·nphase, hidden] — key phase projection
v_proj: QTensor[nh·dv, hidden]
out_proj: QTensor[hidden, nh·dv]
decay: Vec<f64>Per-component decay exp(−exp(A_log)), len nh·2·nphase (precomputed).
k_gate: Option<(QTensor, Vec<f32>)>Selective-write input gate κ (hybrid_k core, stage 71): weight [nh, hidden] + bias [nh]; κ_h = σ(W_k·x + b)_h multiplies the state WRITE (S = decay·S + κ·φk⊗v). None = classic phase core, bit-identical to the pre-κ kernel. Measured at mechanism level: knee ×2–6 earlier, restores correlated-noise robustness, LM crossover vs softmax at SEQ 512 (experiments/lc_final_merged.json).
Auto Trait Implementations§
impl Freeze for VmfPhaseWeights
impl RefUnwindSafe for VmfPhaseWeights
impl Send for VmfPhaseWeights
impl Sync for VmfPhaseWeights
impl Unpin for VmfPhaseWeights
impl UnsafeUnpin for VmfPhaseWeights
impl UnwindSafe for VmfPhaseWeights
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more