Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
timiiowolabi
/
SmolWAM
Like
0
Robotics
Safetensors
nvidia/LIBERO-Cosmos-Policy
English
world-model
world-action-model
imitation-learning
diffusion-transformer
manipulation
libero
edge
License:
nvidia-one-way-noncommercial-license
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
SmolWAM
Commit History
Oct 9
15 days ago
14:30
Teacher compute 42.6 TFLOP (18.5x), the workshop's name, re-rendered comparison video
timiiowolabi
Verified signature
c269c6e
The teacher's compute is now counted like SmolWAM's (attention and the full 33-frame VAE encode included). The workshop is Robot Learning with World Models: Capabilities, Frontiers, and Challenges.
Oct 7
17 days ago
08:08
Model card: list replay.mp4
timiiowolabi
Verified signature
277a26b
08:08
Video preview for the Hub's robotics widget (same comparison video, web-encoded)
timiiowolabi
Verified signature
a74bd05
07:52
SmolWAM 1.0: weights, config, LIBERO text cache, model card
timiiowolabi
Verified signature
91ac4c8
07:49
initial commit
timiiowolabi
Verified signature
dff2822
