Text Generation
PyTorch
English
FockAttentionPARFLM
research
semsimula
conservative-language-model
scalar-potential
lagrangian-mechanics
energy-based-model
physics-informed
fock-attention
parflm
parf
multi-channel-xi
direct-exchange
feynman-diagram
damped-riemannian-geometry
riemannian-geometry
riemannian-geodesics
tinystories
non-transformer
Eval Results (legacy)
Fix: move lambda=0 math outside bold markers for KaTeX rendering
Browse files
README.md
CHANGED
|
@@ -40,7 +40,7 @@ model-index:
|
|
| 40 |
|
| 41 |
# Fock Attention PARFLM (Direct Token-to-Token Exchange Force Language Model)
|
| 42 |
|
| 43 |
-
The **Fock Attention PARFLM** implements the Section 5.1 Feynman diagram as a literal non-conservative force: each token emits a virtual photon carrying a key and payload, and each token absorbs with a query. The exchange coupling \\(\alpha_{ij} = \text{softmax}_j(q_i \cdot k_j / \sqrt{d_k})\\) and the force \\(F_i = \sum_j \alpha_{ij} \cdot v_j\\). This is the
|
| 44 |
|
| 45 |
This "Route 2" across the Conservative Obstruction is the \\(O(T^2)\\) counterpart to the Fock register pool's \\(O(1)\\) "Route 1". It achieves **9.42 PPL** on TinyStories -- slightly behind the register-based Fock-PARFLM v2.1 (9.30), confirming that register persistence provides a small but consistent advantage once routing is fixed.
|
| 46 |
|
|
|
|
| 40 |
|
| 41 |
# Fock Attention PARFLM (Direct Token-to-Token Exchange Force Language Model)
|
| 42 |
|
| 43 |
+
The **Fock Attention PARFLM** implements the Section 5.1 Feynman diagram as a literal non-conservative force: each token emits a virtual photon carrying a key and payload, and each token absorbs with a query. The exchange coupling \\(\alpha_{ij} = \text{softmax}_j(q_i \cdot k_j / \sqrt{d_k})\\) and the force \\(F_i = \sum_j \alpha_{ij} \cdot v_j\\). This is the \\(\lambda = 0\\) **(instantaneous exchange) limit** of the Fock mechanism -- no registers, no persistence, no creation/destruction gates.
|
| 44 |
|
| 45 |
This "Route 2" across the Conservative Obstruction is the \\(O(T^2)\\) counterpart to the Fock register pool's \\(O(1)\\) "Route 1". It achieves **9.42 PPL** on TinyStories -- slightly behind the register-based Fock-PARFLM v2.1 (9.30), confirming that register persistence provides a small but consistent advantage once routing is fixed.
|
| 46 |
|