Grasp Red Act C100 A100 50k is a robotics policy model available on Hugging Face. It implements Action Chunking with Transformers (ACT), an imitation-learning approach designed to predict short sequences of actions, referred to as action chunks, rather than single action steps. The model is trained using teleoperated data and is intended to facilitate robotic policy learning that can often achieve high success rates in its tasks. The model card indicates that Grasp Red Act C100 A100 50k can be used to run policies on robots and to train new policies. It is compatible with the LeRobot library, and instructions are provided for using the model with LeRobot, as well as in environments like Google Colab and Kaggle. The model is distributed in the Safetensors format and is available under the Apache-2.0 license. The evidence does not specify particular use cases, targeted user roles, or detailed deployment requirements beyond its compatibility with LeRobot and support for standard machine learning environments. No information is provided about pricing, beyond the open-source license, nor about specific integrations or supported robotics platforms. Further details on the model's features, training dataset, or evaluation metrics are not included in the provided evidence.
In the Other AI space, Grasp Red Act C100 A100 50k takes a focused approach. It focuses on enabling robots to learn and execute complex action sequences from teleoperated data using open-source models. Grasp Red Act C100 A100 50k is an open-source project aimed at robotics researchers. The project is open source (Apache-2.0). It runs on the web, API, and the command line.
It is developed by eslab1234, and the product first shipped in 2024. The project is developed in the open on GitHub with 25.7k stars and 167 commits in the last 90 days. Across PulseGate's embedding index, Grasp Red Act C100 A100 50k has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are imitation learning, robotics policy, and action chunking.
Latest indexed changes and source events
eslab1234/grasp_red_act_c100_a100_50k discovered by the PulseGate indexer
Other apps tracked under the same category.
