Misha Lvovsky commited on
Commit
99fe89b
·
1 Parent(s): 1fefe90

Update README.md to clarify the purpose of the fork and its modifications

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -6,9 +6,12 @@ tags:
6
  - tokenizer
7
  ---
8
 
 
 
 
 
9
  # FAST: Efficient Action Tokenization for Vision-Language-Action Models
10
 
11
- This is the official repo for the [FAST action tokenizer](https://www.pi.website/research/fast).
12
 
13
  The action tokenizer maps any sequence of robot actions into a sequence of dense, discrete **action tokens** for training autoregressive VLA models.
14
 
 
6
  - tokenizer
7
  ---
8
 
9
+ This is forked from [FAST action tokenizer](https://www.pi.website/research/fast).
10
+
11
+ This fork just adds a slight modification which pads the tokens to make it always output something rather than zeros as it does on errors in the original version.
12
+
13
  # FAST: Efficient Action Tokenization for Vision-Language-Action Models
14
 
 
15
 
16
  The action tokenizer maps any sequence of robot actions into a sequence of dense, discrete **action tokens** for training autoregressive VLA models.
17