AbstractPhil commited on
Commit
46e4939
·
verified ·
1 Parent(s): 112bbeb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -9,6 +9,8 @@ tags:
9
  - experiment
10
  ---
11
 
 
 
12
  A first experiment to test and convert clip-vit-base-patch32 into a geometric model by using only a classification head.
13
 
14
  Below is GPT 5's auto-generated dictation based on the notebook. I'll include the full notebook in a moment here.
@@ -17,6 +19,12 @@ The question was simple; can linear layers learn geometric?
17
 
18
  The answer is... maybe. More research required.
19
 
 
 
 
 
 
 
20
  # Notebook-6 · Crystal-CLIP CIFAR-100
21
 
22
  One-vector image embeddings (HF CLIP) + pentachora vocabulary anchors → cosine-similarity classifier for CIFAR-100.
 
9
  - experiment
10
  ---
11
 
12
+ # Preface
13
+
14
  A first experiment to test and convert clip-vit-base-patch32 into a geometric model by using only a classification head.
15
 
16
  Below is GPT 5's auto-generated dictation based on the notebook. I'll include the full notebook in a moment here.
 
19
 
20
  The answer is... maybe. More research required.
21
 
22
+ # Reasoning
23
+
24
+ I used the 32 dim; as it seemed to be the weakest with flow-match euler-discreet to test the hypothesis that a small dimensional geometry could in fact be used in substitution of a high-geometric variation.
25
+
26
+ The output model is much larger than I wanted; which defeats the purpose of the overall structure - but it's paired directly at the knee with clip-vit-base-patch32, so I'll prepare a decoupled version here in a bit.
27
+
28
  # Notebook-6 · Crystal-CLIP CIFAR-100
29
 
30
  One-vector image embeddings (HF CLIP) + pentachora vocabulary anchors → cosine-similarity classifier for CIFAR-100.