Downloads · 30 days
5
31% of all-time downloads
TangYishan/starvla-qwenoft-franka-robomimic-lift
starvla-qwenoft-franka-robomimic-lift is a image-text-to-text model from TangYishan. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Smoke checkpoint from reproducing examples/realRobots/Franka (no robot). Trained with StarVLA QwenOFT on RoboMimic "Lift" (real Franka, rtbenchmark liftreal/ph) converted to LeRobot v2.1 (180 train episodes, 10,351 fr…
Downloads · 30 days
5
31% of all-time downloads
All-time downloads
16
Public
Repo size
13.4 GB
Likes
0
Public
Click a slice to open those files.
.pt13.4 GB · 100%
From the Hugging Face model README
Smoke checkpoint from reproducing examples/realRobots/Franka (no robot).
Trained with StarVLA QwenOFT on RoboMimic "Lift" (real Franka, rt_benchmark
lift_real/ph) converted to LeRobot v2.1 (180 train episodes, 10,351 frames).
1000 steps / batch 1 / Qwen3.5-0.8B backbone / MLP action head. This is an engineering smoke run, NOT a converged policy — do not use for real deployment.
[dx,dy,dz,droll,dpitch,dyaw,gripper], horizon 16eef_position(3) + eef_rotation(3, axis-angle) (include_state: false)new_embodimentcheckpoints/steps_1000_pytorch_model.pt — DeepSpeed checkpointconfig.yaml / config.full.yaml — training configdataset_statistics.json — normalization statisticssummary.jsonl — step/loss summary