YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

fast-wam

Two Piper real-EEF FastWAM checkpoints, each packed with the code used to train it and an inference entry.

Archive Checkpoint Initialization
fastwam-piper-real-eef-step10000.tar step 10000 official robotwin_uncond_3cam_384.pt, action head reinitialized for 16-D EEF
fastwam-from-clean100k-step10000.tar step 10000 RoboTwin clean front-ROI step_100000, strict load, then real-EEF fine-tune with video loss

Each archive contains checkpoints/step_010000.pt, code/, config.yaml, normalization.json, inference/eef_policy.py, and pretrained/Wan2.2-TI2V-5B (Wan2.2_VAE.pth, models_t5_umt5-xxl-enc-bf16.pth, google/umt5-xxl).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support