openvla
/

openvla-v01-7b

Image-Text-to-Text

feature-extraction

Model card Files Files and versions

skaramcheti commited on Jun 13, 2024

Commit

d1b7313

·

verified ·

1 Parent(s): 5d7672b

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ pipeline_tag: image-text-to-text
 # OpenVLA v0.1 7B
-> *Note*: OpenVLA v0.1 was an early model we trained for development purposes; for our best model, see [openvla/openvla-7b](https://huggingface.co/openvla/openvla-7b).
 OpenVLA v0.1 7B (`openvla-v01-7b`) is an open vision-language-action model trained on 800K robot manipulation episodes from the [Open X-Embodiment](https://robotics-transformer-x.github.io/) dataset (the same mixture used by [Octo](https://octo-models.github.io/)).
 The model takes language instructions and camera images as input and generates robot actions. It supports controlling multiple robots out-of-the-box, and can be quickly adapted for new robot domains via (parameter-efficient) fine-tuning.

 # OpenVLA v0.1 7B
+*Note: OpenVLA v0.1 was an early model we trained for development purposes; for our best model, see [openvla/openvla-7b](https://huggingface.co/openvla/openvla-7b).*
 OpenVLA v0.1 7B (`openvla-v01-7b`) is an open vision-language-action model trained on 800K robot manipulation episodes from the [Open X-Embodiment](https://robotics-transformer-x.github.io/) dataset (the same mixture used by [Octo](https://octo-models.github.io/)).
 The model takes language instructions and camera images as input and generates robot actions. It supports controlling multiple robots out-of-the-box, and can be quickly adapted for new robot domains via (parameter-efficient) fine-tuning.