Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,19 @@
|
|
| 2 |
|
| 3 |
This repository contains BERT-Thetis models with deterministic crystal embeddings.
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
## 📁 Repository Structure
|
| 6 |
|
| 7 |
```
|
|
|
|
| 2 |
|
| 3 |
This repository contains BERT-Thetis models with deterministic crystal embeddings.
|
| 4 |
|
| 5 |
+
I don't like what raw geo-simplex did to Bert without full cantor-stairs control.
|
| 6 |
+
I'm currently working out a way to negate the need for backprop by integrating elements of David,
|
| 7 |
+
but the process isn't immediate. David WORKS because of feature compatability, so enabling education with this
|
| 8 |
+
compatability into other systems is paramount to rapid learning.
|
| 9 |
+
|
| 10 |
+
This version was using the older geometric vocabulary system as a preliminary test and it didn't do very well.
|
| 11 |
+
The next will feature a fully robust cantor stairing system with the vit-beatrix cohesion and full learning k-simplex cantor stairway embeddings.
|
| 12 |
+
|
| 13 |
+
Likely the followup variation will the full David-inspired shunt network that coalesces multiple Bert variants together while simultaneously acting as tiny
|
| 14 |
+
experts in a form of MOE that should enable at least 5 variants of alternative bert models to intercommunicate opinions.
|
| 15 |
+
|
| 16 |
+
Even without my own version of Bert, this can already happen with David I just haven't set it up.
|
| 17 |
+
|
| 18 |
## 📁 Repository Structure
|
| 19 |
|
| 20 |
```
|