Downloads · 30 days
0
XuWuLingYu/LIBERO-HDR-Wan2.2-5BTI2V
LIBERO-HDR-Wan2.2-5BTI2V is a robotics model from XuWuLingYu. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as apache-2.0.
This repository contains LightEWM LIBERO HDR checkpoints based on Wan2.2-TI2V-5B.
Downloads · 30 days
0
Access
Public
Updated Jun 22, 2026
Repo size
32 GB
Likes
0
Public
Click a slice to open those files.
.pt32 GB · 100%
From the Hugging Face model README
This repository contains LightEWM LIBERO HDR checkpoints based on Wan2.2-TI2V-5B.
hdr-video/model.pt: HDR video-only checkpoint trained on LIBERO dense-prompt videos.hdr-video/causal_forcing_config.yaml: training/inference config for the HDR video checkpoint.hdr-actor/model.pt: latest HDR actor checkpoint at step 3600 from the FastWAM-style local video + action branch with the HDR tree prepended.hdr-actor/causal_forcing_config.yaml: training/evaluation config for the HDR actor checkpoint.logs/LIBERO-HDR_train/20260603_041919/checkpoint_model_370000/model.ptlogs/LIBERO-HDR_train_video_action_joint_fastwam_local/20260622_001638/checkpoint_model_003600/model.ptThe HDR actor checkpoint is an in-progress research checkpoint. It is intended for LightEWM closed-loop and open-loop evaluation code rather than a standalone policy API.
Use the corresponding config files with the LightEWM runner/evaluation scripts.