davwer commited on
Commit
9270e65
·
verified ·
1 Parent(s): 82f96c8

Update model card metadata

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -5,7 +5,7 @@ library_name: pytorch
5
  tags:
6
  - interpretability
7
  - activation-probing
8
- - visual-language-models
9
  - temporal
10
  - qwen
11
  ---
@@ -30,7 +30,9 @@ The runtime uses frozen `Qwen/Qwen3.5-0.8B` activations. The public demo path do
30
 
31
  ## Intended Use
32
 
33
- Use these checkpoints with the TM-NLA GitHub repository to run local terminal-based semantic readouts over video windows.
 
 
34
 
35
  The checkpoints are intended for interpretability and research exploration. They are not intended as a production captioner, classifier, benchmark system, or broad video-analysis product.
36
 
@@ -42,4 +44,6 @@ Readouts can be malformed, wrong, generic, or underspecified. The activation ver
42
 
43
  ## Citation
44
 
45
- If you publish work building on this proof of concept, cite or link the companion TM-NLA GitHub repository.
 
 
 
5
  tags:
6
  - interpretability
7
  - activation-probing
8
+ - vision-language-models
9
  - temporal
10
  - qwen
11
  ---
 
30
 
31
  ## Intended Use
32
 
33
+ Use these checkpoints with the TM-NLA GitHub repository to run local terminal-based semantic readouts over video windows:
34
+
35
+ https://github.com/DavWer/TM-NLA
36
 
37
  The checkpoints are intended for interpretability and research exploration. They are not intended as a production captioner, classifier, benchmark system, or broad video-analysis product.
38
 
 
44
 
45
  ## Citation
46
 
47
+ If you publish work building on this proof of concept, cite or link the companion TM-NLA GitHub repository:
48
+
49
+ https://github.com/DavWer/TM-NLA