InternRobotics
/

InternVLA-A1-3B

vision-language-action-model

Model card Files Files and versions

InternVLA-A1-3B

6.72 GB

1 contributor

History: 17 commits

Jia-Zeng's picture

Update checkpoint: pretrained on heterogeneous data sources over real-robot data, synthetic simulation data, and human videos.

08cf716 verified 10 days ago

.gitattributes

1.52 kB

initial commit 2 months ago
README.md

8.77 kB

Update checkpoint: pretrained on heterogeneous data sources over real-robot data, synthetic simulation data, and human videos. 10 days ago
config.json

1.9 kB

Update checkpoint: pretrained on heterogeneous data sources over real-robot data, synthetic simulation data, and human videos. 10 days ago
model.safetensors

6.72 GB
xet

Update checkpoint: pretrained on heterogeneous data sources over real-robot data, synthetic simulation data, and human videos. 10 days ago
stats.json

342 kB

Update checkpoint: pretrained on heterogeneous data sources over real-robot data, synthetic simulation data, and human videos. 10 days ago
train_config.json

137 kB

Update checkpoint: pretrained on heterogeneous data sources over real-robot data, synthetic simulation data, and human videos. 10 days ago