Downloads · 30 days
6
25% of all-time downloads
gen2act-c43-robolab-c39-finetune
trshen925/gen2act-c43-robolab-c39-finetune
gen2act-c43-robolab-c39-finetune is a robotics model from trshen925. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
EMA weights from Gen2Act C43, fine-tuned from the C39 native 7D joint-velocity policy on RoboLab small.
All-time downloads
24
Public
Repo size
1.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.7 GB · 100%
At a glance
- Task
- Robotics
- License
- apache-2.0
- Access
- Public
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026
- SHA
- fa166348
Model card
From the Hugging Face model README
Gen2Act C43 RoboLab C39 fine-tune
EMA weights from Gen2Act C43, fine-tuned from the C39 native 7D joint-velocity policy on RoboLab small.
The released pytorch_model.pt contains model parameters only (the EMA state dict), without optimizer state or training data.
Training used 94 rollout episodes and held out all _env_000 cases (25 episodes) for validation. The epoch-4 checkpoint achieved validation action MAE 0.06865, RMSE 0.10335, and gripper accuracy 84.82%.
Load with the Gen2Act C43 configuration in config.json; this file is a PyTorch state dict and is not a standalone Transformers model.
- Task
- Robotics
- License
- apache-2.0
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026