Commit
·
c00abd5
1
Parent(s):
fbc5da5
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
# Octo Base
|
| 2 |
-
This model is trained with a window size of 2, predicting 7-dimensional actions 4 steps into the future using a diffusion policy.
|
|
|
|
| 3 |
Observations and tasks conform to the following spec:
|
| 4 |
|
| 5 |
Observations:
|
|
|
|
| 1 |
# Octo Base
|
| 2 |
+
This model is trained with a window size of 2, predicting 7-dimensional actions 4 steps into the future using a diffusion policy. The model is a Transformer with 93M parameters (equivalent to a ViT-B). Images are tokenized by preprocessing with a lightweight convolutional encoder, then grouped into 16x16 patches. Language is tokenized by applying the T5 tokenizer, and then applying the T5-Base language encoder.
|
| 3 |
+
|
| 4 |
Observations and tasks conform to the following spec:
|
| 5 |
|
| 6 |
Observations:
|