Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,14 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model:
|
| 4 |
+
- timm/maxvit_tiny_tf_224.in1k
|
| 5 |
+
pipeline_tag: zero-shot-classification
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
Currently it's only a pickled early version at about ~50% accuracy.
|
| 9 |
+
|
| 10 |
+
This one is a 12 layer 8 head variation of max-vit-goliath that trained on geometric vocab with cifar100 using a specialized 5d format. It's WORKING - somewhat, but it's definitely nothing to phone home about yet.
|
| 11 |
+
|
| 12 |
+
Dropout was used and I really don't like what it did to the internals. The math doesn't line up correctly and the shapes are all over the board. The next will be cleaner.
|
| 13 |
+
|
| 14 |
+
I've included the weights in a file for posterity as this may be abandoned, but I want to preserve the A100 80 gig time that google sliced off for me yesterday. If that was intentional thank you, if it was random then the universe wanted thsi to exist. Either way we're here now.
|