[DO NOT MERGE] HF model cards for ckpts & datasets

hf_model_cards/Arena-G1-Loco-Manipulation-Task/readme.md

@@ -0,0 +1,105 @@
+---
+license: cc-by-4.0
+task_categories:
+- robotics
+tags:
+- robotics
+---
+## Dataset Description:
+
+This dataset is multimodal collections of trajectories generated in Isaac Lab. It supports humanoid (G1) loco-manipulation task in IsaacLab-Arena enviorment. Each entry provides the full context (state, vision, language, action) needed to train and evaluate generalist robot policies for box pick and place task.
+
+| Dataset Name              | # Trajectories |
+|---------------------------|----------------|
+| G1 Loco-Manipulation Task | 50             |
+
+This dataset is ideal for behavior cloning, policy learning, and generalist robotic (loco) manipulation research. It has been for post-training GR00T N1.5 model.
+
+This dataset is ready for commercial use.
+
+## Dataset Owner
+NVIDIA Corporation
+
+## Dataset Creation Date:
+10/10/2025
+
+## License/Terms of Use:
+This dataset is governed by the Creative Commons Attribution 4.0 International License (CC-BY-4.0).
+
+## Intended Usage:
+This dataset is intended for:
+
+- Training robot manipulation policies using behavior cloning.
+- Research in generalist robotics and task-conditioned agents.
+- Sim-to-real / Sim-to-Sim transfer studies.
+
+## Dataset Characterization:
+### Data Collection Method
+
+- Automated
+- Automatic/Sensors
+- Synthetic
+
+5 human teleoperated demonstrations are collected through a depth camera and keyboard in Isaac Lab. All 50 demos are generated automatically using a synthetic motion trajectory generation framework, Mimicgen [1]. Each demo is generated at 50 Hz.
+
+### Labeling Method
+
+Not Applicable
+
+## Dataset Format:
+We provide a few dataset files, including
+- a human-annoated 5 demonstrations in HDF5 dataset file (`arena_g1_loco_manipulation_dataset_annotated.hdf5`)
+- a Mimic-generated 1 demostration in HDF5 dataset file (`arena_g1_loco_manipulation_dataset_generated_small.hdf5`)
+- a Mimic-generated 50 demonstrations in HDF5 dataset file (`arena_g1_loco_manipulation_dataset_generated.hdf5`)
+- a GR00T-Lerobot formatted dataset converted from the Mimic-generated HDF5 dataset file (`lerobot`)
+- 
+Each demo in GR00T-Lerobot datasets consists of a time-indexed sequence of the following modalities:
+
+### Actions
+- action (FP64): joint desired positions for all body joints (26 DoF)
+
+### Observations
+- observation.state (FP64): joint positions for all body joints (26 DoF)
+
+### Task-specific
+- timestamp (FP64): simulation time in seconds of each recorded data entry.
+- annotation.human.action.task_description (INT64): index referring to the language instruction recorded in the metadata
+- annotation.human.action.valid (INT64): index indicating validity of annotaion recorded in the metadata
+- episode_index (INT64): index indicating the order of each demo
+- task_index (INT64): index used in multi-task data loader. Not applicable to Gr00t-N1 post training, always set to 0.
+
+
+### Videos
+- 256 x 256 RGB videos in mp4 format from first-person-view camera
+
+In additional, a set of metadata describing the followings is provided,
+- `episodes.jsonl` contains a list of all the episodes in the entire dataset. Each episode contains a list of tasks and the length of the episode.
+- `tasks.jsonl` contains a list of all the tasks in the entire dataset.
+- `modality.json` contains the modality configuration.
+- `info.json` contains the dataset information.
+
+
+## Dataset Quantification:
+
+### Record Count
+
+#### G1 Loco-Manipulation Task
+- Number of demonstrations/trajectories: 50
+- Number of RGB videos: 50
+
+### Total Storage
+
+24.1 GB
+
+## Ethical Considerations:
+NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. 
+
+Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
+
+## Reference(s):
+[1] @inproceedings{mandlekar2023mimicgen,
+    title={MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations},
+    author={Mandlekar, Ajay and Nasiriany, Soroush and Wen, Bowen and Akinola, Iretiayo and Narang, Yashraj and Fan, Linxi and Zhu, Yuke and Fox, Dieter},
+    booktitle={7th Annual Conference on Robot Learning},
+    year={2023}
+    }

hf_model_cards/Arena-GR1-Manipulation-Task/readme.md

@@ -0,0 +1,105 @@
+---
+license: cc-by-4.0
+task_categories:
+- robotics
+tags:
+- robotics
+---
+## Dataset Description:
+
+This dataset is multimodal collections of trajectories generated in Isaac Lab. It supports humanoid (GR1) manipulation task in IsaacLab-Arena enviorment. Each entry provides the full context (state, vision, language, action) needed to train and evaluate generalist robot policies for opening microwave task.
+
+| Dataset Name          | # Trajectories |
+|-----------------------|----------------|
+| GR1 Manipulation Task | 50             |
+
+This dataset is ideal for behavior cloning, policy learning, and generalist robotic manipulation research. It has been for post-training GR00T N1.5 model.
+
+This dataset is ready for commercial use.
+
+## Dataset Owner
+NVIDIA Corporation
+
+## Dataset Creation Date:
+10/10/2025
+
+## License/Terms of Use:
+This dataset is governed by the Creative Commons Attribution 4.0 International License (CC-BY-4.0).
+
+## Intended Usage:
+This dataset is intended for:
+
+- Training robot manipulation policies using behavior cloning.
+- Research in generalist robotics and task-conditioned agents.
+- Sim-to-real / Sim-to-Sim transfer studies.
+
+## Dataset Characterization:
+### Data Collection Method
+
+- Automated
+- Automatic/Sensors
+- Synthetic
+
+10 human teleoperated demonstrations are collected through a depth camera and keyboard in Isaac Lab. All 50 demos are generated automatically using a synthetic motion trajectory generation framework, Mimicgen [1]. Each demo is generated at 50 Hz.
+
+### Labeling Method
+
+Not Applicable
+
+## Dataset Format:
+We provide a few dataset files, including
+
+- a human-annoated 10 demonstrations in HDF5 dataset file (`arena_gr1_manipulation_dataset_annotated.hdf5`)
+- a Mimic-generated 50 demonstrations in HDF5 dataset file (`arena_gr1_manipulation_dataset_generated.hdf5`)
+- a GR00T-Lerobot formatted dataset converted from the Mimic-generated HDF5 dataset file (`lerobot`)
+
+Each demo in GR00T-Lerobot datasets consists of a time-indexed sequence of the following modalities:
+
+### Actions
+- action (FP64): joint desired positions for all body joints (36 DoF)
+
+### Observations
+- observation.state (FP64): joint positions for all body joints (54 DoF)
+
+### Task-specific
+- timestamp (FP64): simulation time in seconds of each recorded data entry.
+- annotation.human.action.task_description (INT64): index referring to the language instruction recorded in the metadata
+- annotation.human.action.valid (INT64): index indicating validity of annotaion recorded in the metadata
+- episode_index (INT64): index indicating the order of each demo
+- task_index (INT64): index used in multi-task data loader. Not applicable to Gr00t-N1 post training, always set to 0.
+
+
+### Videos
+- 512 x 512 RGB videos in mp4 format from first-person-view camera
+
+In additional, a set of metadata describing the followings is provided,
+- `episodes.jsonl` contains a list of all the episodes in the entire dataset. Each episode contains a list of tasks and the length of the episode.
+- `tasks.jsonl` contains a list of all the tasks in the entire dataset.
+- `modality.json` contains the modality configuration.
+- `info.json` contains the dataset information.
+
+
+## Dataset Quantification:
+
+### Record Count
+
+#### GR1 Manipulation Task
+- Number of demonstrations/trajectories: 50
+- Number of RGB videos: 50
+
+### Total Storage
+
+5.16 GB
+
+## Ethical Considerations:
+NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. 
+
+Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
+
+## Reference(s):
+[1] @inproceedings{mandlekar2023mimicgen,
+    title={MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations},
+    author={Mandlekar, Ajay and Nasiriany, Soroush and Wen, Bowen and Akinola, Iretiayo and Narang, Yashraj and Fan, Linxi and Zhu, Yuke and Fox, Dieter},
+    booktitle={7th Annual Conference on Robot Learning},
+    year={2023}
+    }

hf_model_cards/GN1x-Tuned-Arena-G1-Loco-Manipulation/readme.md

@@ -0,0 +1,115 @@
+---
+datasets:
+- nvidia/Arena-G1-Loco-Manipulation-Task
+tags:
+- robotics
+---
+
+<div align="center">
+  <a href="https://github.com/isaac-sim/IsaacLab-Arena">
+    <img src="https://img.shields.io/badge/GitHub-grey?logo=GitHub" alt="GitHub Badge">
+  </a>
+  <a href="https://fictional-disco-qm1zq12.pages.github.io/html/index.html">
+    <img src="https://img.shields.io/badge/Website-green" alt="Website Badge">
+  </a>
+</div>
+
+## Description:
+
+This is a fine tuned NVIDIA Isaac GR00T N1.5 model for the locomanipulation pick and place task provided in IsaacLab Arena.<br><br>
+Isaac `GR00T N1.5-3B` is the medium-sized version of our model built using pre-trained vision and language encoders, and uses a flow matching action transformer to model a chunk of actions conditioned on vision, language and proprioception.<br><br>
+This model is ready for non-commercial use.
+
+## License/Terms of Use
+[Nvidia License](https://developer.download.nvidia.com/licenses/NVIDIA-OneWay-Noncommercial-License-22Mar2022.pdf?t=eyJscyI6ImdzZW8iLCJsc2QiOiJodHRwczovL3d3dy5nb29nbGUuY29tLyIsIm5jaWQiOiJzby15b3V0LTg3MTcwMS12dDQ4In0=)<br>
+You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws. <br>
+
+### Deployment Geography:
+Global
+
+### Use Case:
+Researchers, Academics, Open-Source Community: AI-driven robotics research and algorithm development.
+Developers: Integrate and customize AI for various robotic applications.
+Startups & Companies: Accelerate robotics development and reduce training costs.
+
+## Reference(s):
+[NVIDIA-GR00T N1:](https://arxiv.org/abs/2503.14734)
+"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots" arXiv preprint arXiv:2503.14734 (2025).<br>
+NVIDIA-EAGLE:
+Li, Zhiqi, et al. "Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models." arXiv preprint arXiv:2501.14818 (2025).<br>
+[Rectified Flow:](https://arxiv.org/abs/2209.03003)
+Liu, Xingchao, and Chengyue Gong. "Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow." The Eleventh International Conference on Learning Representations”.<br>
+Flow Matching Policy:
+Black, Kevin, et al. "π0: A Vision-Language-Action Flow Model for General Robot Control." arXiv preprint arXiv:2410.24164 (2024).<br>
+
+## Model Architecture:
+**Architecture Type:** Vision Transformer, Multilayer Perceptron, Flow matching Transformer
+
+Isaac GR00T N1.5 uses vision and text transformers to encode the robot's image observations and text instructions. The architecture handles a varying number of views per embodiment by concatenating image token embeddings from all frames into a sequence, followed by language token embeddings. 
+
+To model proprioception and a sequence of actions conditioned on observations, Isaac GR00T N1.5-3B uses a flow matching transformer. The flow matching transformer interleaves self-attention over proprioception and actions with cross-attention to the vision and language embeddings. During training, the input actions are corrupted by randomly interpolating between the clean action vector and a gaussian noise vector. At inference time, the policy first samples a gaussian noise vector and iteratively reconstructs a continuous-value action using its velocity prediction.
+
+In GR00T-N1.5, the MLP connector between the vision-language features and the diffusion-transformer (DiT) has been modified for improved performance on our sim benchmarks. Also, it was trained jointly with flow matching and world-modeling objectives.
+
+**Network Architecture:** 
+![image/png](https://github.com/NVIDIA/Isaac-GR00T/blob/main/media/model-architecture.png?raw=true)
+The schematic diagram is shown in the illustration above.
+Red, Green, Blue (RGB) camera frames are processed through a pre-trained vision transformer (SigLip2).
+Text is encoded by a pre-trained transformer (T5)
+Robot proprioception is encoded using a multi-layer perceptron (MLP) indexed by the embodiment ID. To handle variable-dimension proprio, inputs are padded to a configurable max length before feeding into the MLP.
+Actions are encoded and velocity predictions decoded by an MLP, one per unique embodiment.
+The flow matching transformer is implemented as a diffusion transformer (DiT), in which the diffusion step conditioning is implemented using adaptive layernorm (AdaLN).
+
+## Input:
+**Input Type:**
+* Vision: Image Frames<br>
+* State: Robot Proprioception<br>
+* Language Instruction: Text<br>
+
+**Input Format:**
+* Vision: Variable number of 256x256 uint8 image frames, coming from robot cameras<br>
+* State: Floating Point<br>
+* Language Instruction: String<br>
+
+**Input Parameters:**
+* Vision: 2D - RGB image, square<br>
+* State: 1D - Floating number vector<br>
+* Language Instruction: 1D - String<br>
+
+## Output:
+**Output Type(s):** Actions<br>
+**Output Format** Continuous-value vectors<br>
+**Output Parameters:** [Two-Dimensional (2D)] <br>
+**Other Properties Related to Output:** Continuous-value vectors correspond to different motor controls on a robot, which depends on Degrees of Freedom of the robot embodiment.
+
+Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. <br>
+
+## Software Integration:
+**Runtime Engine(s):** PyTorch
+
+**Supported Hardware Microarchitecture Compatibility:** 
+All of the below:
+* NVIDIA Ampere
+* NVIDIA Blackwell
+* NVIDIA Jetson
+* NVIDIA Hopper
+* NVIDIA Lovelace
+
+**[Preferred/Supported] Operating System(s):**
+* Linux
+
+## Model Version(s):
+Version 1.5.
+
+## Ethical Considerations:
+NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.  
+
+For more detailed information on ethical considerations for this model, please see the Model Card++ [Explainability](https://huggingface.co/nvidia/GR00T-N1.5-3B/blob/main/EXPLAINABILITY.md), [Bias](https://huggingface.co/nvidia/GR00T-N1.5-3B/blob/main/BIAS.md), [Safety & Security](https://huggingface.co/nvidia/GR00T-N1.5-3B/blob/main/SAFETY_and_SECURITY.md)), and [Privacy](https://huggingface.co/nvidia/GR00T-N1.5-3B/blob/main/PRIVACY.md) Subcards.
+
+Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
+
+## Resources
+
+* Previous Version: https://huggingface.co/nvidia/GR00T-N1-2B<br>
+* Blogpost: https://nvidianews.nvidia.com/news/foundation-model-isaac-robotics-platform
+* Community Article with the tutorial how to finetune on SO100/101: https://huggingface.co/blog/nvidia/gr00t-n1-5-so101-tuning