MLX
German
English
Mixture of Experts
multimodal
vision
audio
endtoend
j.o.s.i.e.
Isaak-Carter commited on
Commit
5c1268c
1 Parent(s): 48bd624

Update Version4.7-architecture.txt

Browse files
Files changed (1) hide show
  1. Version4.7-architecture.txt +1 -1
Version4.7-architecture.txt CHANGED
@@ -4,7 +4,7 @@ Josiev47(
4
  (vision): RGBDTPreprocessor(
5
  (rgbt_stem): PatchEmbedGeneric(
6
  (proj): Sequential(
7
- (0): PadIm2Video()
8
  (1): Conv3d(3, {llm_in_embedding}, kernel_size=(2, 14, 14), stride=(2, 14, 14), bias=False)
9
  )
10
  (norm_layer): RMSNorm()
 
4
  (vision): RGBDTPreprocessor(
5
  (rgbt_stem): PatchEmbedGeneric(
6
  (proj): Sequential(
7
+ (0): make_image_to_video()
8
  (1): Conv3d(3, {llm_in_embedding}, kernel_size=(2, 14, 14), stride=(2, 14, 14), bias=False)
9
  )
10
  (norm_layer): RMSNorm()