add gpt2 and decoder
Browse files- README.md +1 -1
- decoder.onnx +3 -0
- gpt2.onnx +3 -0
README.md
CHANGED
|
@@ -5,6 +5,6 @@ pipeline_tag: robotics
|
|
| 5 |
---
|
| 6 |
|
| 7 |
This model has been trained on a larger version of the commabody dataset.
|
| 8 |
-
It includes a [vqgan](https://github.com/CompVis/taming-transformers) encoder/decoder fine tuned from imagenet. It compresses images of size
|
| 9 |
|
| 10 |
It also includes a GPT2 model trained to predict the next frame, wheel speeds and actions. It can be used either as a simulator or as a policy.
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
This model has been trained on a larger version of the commabody dataset.
|
| 8 |
+
It includes a [vqgan](https://github.com/CompVis/taming-transformers) encoder/decoder fine tuned from imagenet. It compresses images of size 160x256 to 10x16 tokens.
|
| 9 |
|
| 10 |
It also includes a GPT2 model trained to predict the next frame, wheel speeds and actions. It can be used either as a simulator or as a policy.
|
decoder.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35162442f650c4b078f204a23a70986c6181e5eb73c67e31273a6a41981918e6
|
| 3 |
+
size 171244941
|
gpt2.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a47d934f7e6c6e5ea4cbd39e9424e66ae9e1fbf0007f08b08f4bb33be363ad6e
|
| 3 |
+
size 399390835
|