OpenVLA 7B (openvla-7b) is an open vision-language-action model trained on 970K robot manipulation episodes from the Open X-Embodiment dataset. The model takes language instructions and camera images as input and generates robot actions. It supports controlling multiple robots out-of-the-box, and can be quickly adapted for new robot domains via (parameter-efficient) fine-tuning. All OpenVLA checkpoints, as well as our training codebase are released under an MIT License. For full details, please read our paper and see our project page. OpenVLA models take a language instruction and a camera image of a robot workspace as input, and predict (normalized) robot actions consisting of 7-DoF…
Open weights
mit
7.5B parameters
transformers
SmolVLA is a compact, efficient Vision-Language-Action (VLA) model designed for affordable robotics, trainable on a single GPU and deployable on consumer hardware, while matching the performance of much larger VLAs through community-driven data. Original paper: (SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics)[https://arxiv.org/abs/2506.01844] For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation If you’re training / fine-tuning, you typically call forward(...) to get a loss and then: - -policy.chunksize=... - -policy.nactionsteps=...…
Open weights
apache-2.0
450M parameters
lerobot
NVIDIA Isaac GR00T N1.7 is an open foundation model for generalized humanoid robot reasoning and skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. Developers and researchers can post-train GR00T N1.7 with real or synthetic data for their specific humanoid robot or task. Isaac GR00T N1.7 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. A detailed description of the Isaac GR00T N1.X architecture is provided in the GROOT N1 White…
Open weights
3.1B parameters
LIBERO 4in1（liberospatial / liberoobject / liberogoal / libero10）共 53.19 GB 的 Wan2.2-VAE 编码 latent 缓存： 训练 LIBERO policy（action head / VLA）时直接读取 latent 缓存，避免重复 VAE 编码。 - 窗口模式: windowed（--windowed） - 输出:.pt 文件，每 episode 一个 - dataset（推荐）: https://huggingface.co/datasets/MangoGoes/libero4in1wan2.2vaelatentdataset - model（本仓库）: https://huggingface.co/MangoGoes/libero4in1wan2.2vaelatentcosmosstyle
Open weights
other
cosmos
π₀ is a Vision-Language-Action (VLA) foundation model from Physical Intelligence that jointly reasons over vision, language, and actions to control robots, serving as the base architecture that later enabled π₀.₅’s open-world generalization. Original paper: π0: A Vision-Language-Action Flow Model for General Robot Controlion For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation If you’re training / fine-tuning, you typically call forward(...) to get a loss and then: - -policy.chunksize=... - -policy.nactionsteps=... - -policy.maxactiontokens=...…
Open weights
gemma
3.5B parameters
lerobot
Alpamayo 1.5 is a significant update to NVIDIA’s open 10B-parameter chain-of-thought reasoning VLA model, designed to be an interactive and steerable reasoning engine for the AV community. Alpamayo 1.5 is built on the Cosmos-Reason2 VLM backbone, is RL post-trained, and introduces support for navigation guidance, flexible camera counts, and user question answering. This model is ready for non-commercial use. Commercial licensing available upon request. Model weights: The model weights are released under the OpenMDW-1.1 license. Source code: Apache License 2.0, as provided in the Alpamayo 1.5 source repository. Global Researchers and autonomous-driving practitioners who are developing and…
Open weights
openmdw-1.1
11.1B parameters
NVIDIA Isaac GR00T N1.6 is an open vision-language-action (VLA) model for generalized humanoid robot skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. GR00T N1.6 is trained on a diverse mixture of robot data including bimanual, semi-humanoid and an expansive humanoid dataset, consisting of real captured data, synthetic data generated using the components of NVIDIA Isaac GR00T Blueprint. It is adaptable through post-training for specific embodiments, tasks and environments. The neural network architecture of GR00T N1.6 is a combination of vision-language foundation model and diffusion transformer…
Open weights
3.3B parameters
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open weights
apache-2.0
605M parameters
lerobot
π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Checkpoint trained and evaluated on LIBERO tasks Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full…
Open weights
gemma
3.6B parameters
lerobot
π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full installation details (including optional video…
Open weights
gemma
3.6B parameters
lerobot
MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER, an embodied-reasoning VLM backbone, and connects the autoregressive VLM to a flow-matching continuous action expert through per-layer KV (key-value) conditioning. This checkpoint is the post-trained, multi-embodiment MolmoAct2 model. It is intended as a foundation checkpoint for further robot fine-tuning rather than as a ready-to-run policy for a single deployment setting. Use this checkpoint for further fine-tuning on a target robot embodiment or benchmark. It contains the VLM and continuous action expert weights, plus normalization metadata for the post-training mixture in normstats.json. This…
Open weights
5.4B parameters
16,384 tokens
transformers
MolmoAct2-Think extends MolmoAct2 with depth-token reasoning. Before producing an action, the model can predict a compact 10 x 10 discrete depth representation and condition the action expert on the resulting depth-aware VLM cache. This checkpoint is the post-trained, multi-embodiment depth-reasoning model. It is intended as a foundation checkpoint for further robot fine-tuning rather than as a ready-to-run policy for a single deployment setting. Use this checkpoint for further fine-tuning when the downstream policy should use depth reasoning. It contains the VLM, action expert, and depth-token weights, plus normalization metadata for the post-training mixture in normstats.json. This model…
Open weights
5.4B parameters
16,384 tokens
transformers
MolmoAct2-Pretrain adapts the Molmo2-ER vision-language backbone into a discrete autoregressive robot policy while keeping the Molmo2 token interface. Robot state is represented with discrete state tokens, and future one-second actions are represented with OpenFAST action tokens. This checkpoint is the pre-trained VLA backbone before the continuous flow-matching action expert is attached. It is intended for further post-training or fine-tuning, not direct continuous-control inference. Use this checkpoint for further MolmoAct2 training stages. It was converted with addactionexpert=false, so predictaction(...) is intentionally unavailable. Standard Transformers generation can still be used…
Open weights
4.9B parameters
16,384 tokens
transformers
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open weights
apache-2.0
450M parameters
lerobot
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Spatial, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
Alpamayo 2 Super is a 34B-parameter foundation model designed to tackle multiple autonomous vehicle (AV) development tasks. It combines a 32B VLM backbone with a 2B diffusion expert. Alpamayo 2 Super was developed by NVIDIA as a part of the broader Alpamayo Open Platform. Model weights: The model weights are released under the OpenMDW-1.1 license. Source code: Apache License 2.0, as provided in the Alpamayo 2 Super source repository. Global Developers and researchers working on autonomous vehicle systems who need a foundation model for perception, planning, and decision-making tasks. Alpamayo 2 Super supports multiple AV development tasks such as trajectory prediction, visual question…
Open weights
openmdw-1.1
35.8B parameters
Note: Following the release of NVIDIA Alpamayo at CES 2026, Alpamayo-R1 has been renamed to Alpamayo 1. Alpamayo 1 integrates Chain-of-Causation reasoning with trajectory planning to enhance decision-making in complex autonomous-driving scenarios. Alpamayo 1 (v1.0) was developed by NVIDIA as a vision-language-action (VLA) model that bridges interpretable reasoning with precise vehicle control for autonomous-driving applications. This model is ready for non-commercial use. Commercial licensing available upon request. Model weights: The model weights are released under the OpenMDW-1.1 license. Source code: Apache License 2.0, as provided in the Alpamayo 1 source repository. Global Researchers…
Open weights
openmdw-1.1
11.1B parameters
transformers
Paper: Zheng et al., 2025, “X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model” (arXiv:2510.10274) Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich robotic data sources, X-VLA introduces a Soft Prompt approach with minimally added parameters: we infuse prompt-learning concepts into cross-embodiment robot learning, introducing separate sets of learnable embeddings for each distinct embodiment. These embodiment-specific prompts empower VLA models to exploit cross-embodiment…
Open weights
apache-2.0
880M parameters
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open weights
apache-2.0
5.6B parameters
lerobot
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Object, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Goal, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
Flash Vision-Language-Action Inference for Autonomous Driving FlashDrive accelerates Alpamayo 1.5 — one of NVIDIA's 10B-parameter vision-language-action models for autonomous driving — by 4.7× with no loss in accuracy, through streaming inference, DFlash speculative reasoning, ParoQuant W4A8 quantization, adaptive action caching, and torch.compile. This repository mirrors the weights of nvidia/Alpamayo-1.5-10B and is the base checkpoint of the FlashDrive stack. Loading it pulls the derived companions automatically: Install FlashDrive, then load this base checkpoint — the -PARO and -DFlash companions are fetched automatically: The first call per stream only prefills the KV cache and returns…
Open weights
other
11.1B parameters
MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the SO-100/101 mixture with absolute joint-pose control and annotated language instructions. It is intended for both further fine-tuning and SO-100/101 policy inference. Use this checkpoint for SO-100/101 inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="so100so101molmoact2" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete…
Open weights
5.4B parameters
16,384 tokens
transformers
MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the full LIBERO training mixture, combining Spatial, Object, Goal, and Long suites. It is intended for both further fine-tuning and LIBERO policy inference. Use this checkpoint for LIBERO inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="libero" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete action prediction is exposed for…
Open weights
5.4B parameters
16,384 tokens
transformers
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open weights
apache-2.0
450M parameters
lerobot
Flash Vision-Language-Action Inference for Autonomous Driving DFlash draft model for z-lab/Alpamayo-1.5-10B, used by FlashDrive to accelerate the chain-of-causation reasoning of Alpamayo 1.5. DFlash (ICML 2026) uses a lightweight block-diffusion draft to propose several tokens in parallel; the target verifies each block in a single forward, preserving its output distribution. This draft is a 2-layer Qwen3-style network (block size 8) conditioned on target hidden states from layers 24/30/31/32/34. The repository also ships maskembedding.pt, the trained mask-token embedding FlashDrive appends to the target's embedding table. See the base model card and the FlashDrive repository for the full…
Open weights
other
470M parameters
40,960 tokens
π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full installation details (including optional video…
Open weights
gemma
3.6B parameters
lerobot
Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured settings. Yet it remains an open question whether current VLA systems can benefit from more effective architectural design, scale to substantially larger and more heterogeneous data regimes, and achieve broader generalization across tasks and embodiments. To this end, we present GigaBrain-0.7, an embodied foundation model with substantially improved generalization across diverse robot embodiments. Specifically, GigaBrain-0.7 unifies understanding, prediction, and action through a three-system architecture, scales…
Open weights
apache-2.0
4.1B parameters
diffusers
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Long (also called LIBERO-10), as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
NVIDIA Isaac GR00T N1.7 is an open foundation model for generalized humanoid robot reasoning and skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. Developers and researchers can post-train GR00T N1.7 with real or synthetic data for their specific humanoid robot or task. Isaac GR00T N1.7 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. A detailed description of the Isaac GR00T N1.X architecture is provided in the GROOT N1 White…
Open weights
3.1B parameters
This repository contains a checkpoint of the Pi0 model (HF implementation | Paper) finetuned on the BridgeV2 dataset for robotic manipulation tasks. The model is later used for testing on the Simpler Environment and our INTACT Probing Suite for the generalization boundaries of VLA models. Paper: From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models Or directly in python with Lerobot, see blow: First, install lerobot Then For more details please refer to our paper and code Checkpoint choice After training 15 epochs, we sweep the checkpoint at epoch 1, 2, 3, 4, 5, 10, 15 for performance on the original 4 Bridge tasks in the SimplerEnv, and choose…
Open weights
apache-2.0
3.2B parameters
transformers
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open weights
apache-2.0
5.6B parameters
lerobot
X-VLA is a Vision-Language-Action foundation model that uses soft prompts to handle cross-embodiment and cross-domain robot control within a unified Transformer architecture. Original paper: X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation If you’re training / fine-tuning, you typically call forward(...) to get a loss and then: - -policy.chunksize=... - -policy.nactionsteps=... - -policy.maxactiontokens=... - -policy.gradientcheckpointing=true You can use the record…
Open weights
apache-2.0
880M parameters
lerobot
The MoT design keeps a visual expert stream (reference + future latents) and an action expert stream (state + action), with multi-modal self-attention across both. Weights are sharded at ~10GB per file. This repo contains the transformer only; runtime also needs the Wan2.2 VAE / scheduler from the base Diffusers checkpoint. For usage, training, and inference details, see our open source code page.
Open weights
apache-2.0
6B parameters
diffusers
Wan2.2-TI2V-5B video DiT + 48-joint action head, trainingmode=joint. The base is suhyeok's finalized B-method recipe: a teacher-forced (sigma=0.25) self-EMA teacher plus an iBOT prototype loss at L18 L18, gamma=0.01, two-view. On top of it the 3 PAST cond latent frames are pooled into one motion frame before a chosen block. These are NOT the surrogate ctxpool runs. The surrogate line (older base, pd8 x GA1) lives in hmkang/wamctxpoolxattn and hmkang/wamctxpoolavg. Do not compare across the two sets. Geometry: 4-latin (numframesin=25, numframesout=41, fdf 2) = 4 cond + 2 future latent slots, 96 tokens per latent frame, 576 tokens per row. Effective batch 16 clips x GA 2 x 2 views = 64 rows…
Open weights
apache-2.0
wan2.2
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Spatial, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
2,048 tokens
transformers
This repository contains the OpenVLA-OFT checkpoint trained on 4 LIBERO task suites combined (-Spatial, -Object, -Goal, -Long), as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
Action Chunking Transformer Policy (as per Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware) trained for the AlohaTransferCube environment from gym-aloha. See the LeRobot library (particularly the evaluation script) for instructions on how to load and evaluate this model. Trained with LeRobot@3c0a209. The model was trained using LeRobot's training script and with the alohasimtransfercubehuman dataset, using this command: The training curves may be found at https://wandb.ai/aliberts/lerobot/runs/720l37xb. The current model corresponds to the checkpoint at 80k steps. This took about 1h45 to train on an Nvida A100. The model was evaluated on the AlohaTransferCube task from…
Open weights
apache-2.0
52M parameters
transformers
Diffusion Policy (as per Diffusion Policy: Visuomotor Policy Learning via Action Diffusion) trained for the PushT environment from gym-pusht. See the LeRobot library (particularly the evaluation script) for instructions on how to load and evaluate this model. Trained with LeRobot@3c0a209. The model was trained using LeRobot's training script and with the pusht dataset, using this command: The training curves may be found at https://wandb.ai/aliberts/lerobot/runs/s7elvf4r. The current model corresponds to the checkpoint at 175k steps. The model was evaluated on the PushT environment from gym-pusht and compared to a similar model trained with the original Diffusion Policy code. There are two…
Open weights
apache-2.0
263M parameters
transformers
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open weights
apache-2.0
5.6B parameters
lerobot
π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and…
Open weights
apache-2.0
4.1B parameters
lerobot
weighted/imatrix quants of https://huggingface.co/DeepCybo/PhysBrain1.5-8B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/PhysBrain1.5-8B-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
Open weights
transformers
Paper: Zheng et al., 2025, “X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model” (arXiv:2510.10274) Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich robotic data sources, X-VLA introduces a Soft Prompt approach with minimally added parameters: we infuse prompt-learning concepts into cross-embodiment robot learning, introducing separate sets of learnable embeddings for each distinct embodiment. These embodiment-specific prompts empower VLA models to exploit cross-embodiment…
Open weights
apache-2.0
880M parameters
[[Paper]](https://arxiv.org/pdf/2505.13441) [[arXiv]](https://arxiv.org/abs/2505.13441) [[Project Website]](https://abhaybd.github.io/GraspMolmo/) [[Data]](https://huggingface.co/datasets/allenai/PRISM) GraspMolmo is a generalizable open-vocabulary task-oriented grasping (TOG) model for robotic manipulation. Given an image and a task to complete (e.g. "Pour me some tea"), GraspMolmo will point to the most appropriate grasp location, which can then be matched to the closest stable grasp. Running the above code could result in the following output: To predict a grasp point and match it to one of the candidate grasps, refer to the GraspMolmo class. First, install graspmolmo with and then…
Open weights
mit
8B parameters
4,096 tokens
MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the bimanual YAM mixture with absolute joint-pose control and annotated language instructions. It is intended for both further fine-tuning and bimanual YAM policy inference. Use this checkpoint for bimanual YAM inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="yamdualmolmoact2" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete…
Open weights
5.4B parameters
16,384 tokens
transformers
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot smolvla guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI…
Open weights
apache-2.0
450M parameters
lerobot
lerobot/smolvlabase fine-tuned on Prashant-77/thaliall (1050 scripted-expert episodes, 7 skills, language-conditioned, 3 cameras). Camera keys are renamed at train and inference time: overhead → camera1, wrista → camera2, wristb → camera3 (--renamemap; runtime/executors.py applies the same map). Checkpoints in this repo. Root = 20 000 total steps. step14000/ = the best per-skill checkpoint (14 000 steps at batch 16 on a T4; the last 6 000 steps ran at batch 4 with a fresh optimizer on a smaller GPU and lost ground). Policy-only success per skill from task-consistent start states, 20 held-out seeds (eval/skilleval.py --kind smolvla): The scripted expert reaches 9/10 on the full task; the…
Open weights
apache-2.0
450M parameters
lerobot
Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot act guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning…
Open weights
apache-2.0
52M parameters
lerobot
Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot act guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning…
Open weights
apache-2.0
52M parameters
lerobot
Full fine-tune of lerobot/pi05base on a bimanual actuator-unboxing task, with a speed token in the text prompt: Part of a check whether pi0.5 can be conditioned through text tokens, as a precursor to advantage conditioning (RECAP, π0.6). Data (not on the Hub): 198 teleoperated episodes (50 fps, three 224×224 cameras, 14-D state and action) labelled slow, plus two 2× copies of every episode that keep only the even or only the odd frames, labelled fast (594 episodes, 348,616 frames). Slow and fast samples show the same images, so only the token tells them apart. 30 % of training samples get unknown, the null prompt for classifier-free guidance. Training: 4,000 steps (about 3 epochs), batch…
Open weights
3.4B parameters
lerobot
Full fine-tune of lerobot/pi05base on a bimanual actuator-unboxing task, with a speed token in the text prompt: Part of a check whether pi0.5 can be conditioned through text tokens, as a precursor to advantage conditioning (RECAP, π0.6). Data (not on the Hub): 198 teleoperated episodes labelled slow, merged with 437 episodes of the same task demonstrated about 1.75× faster in another session, labelled fast (635 episodes, 371,523 frames; 50 fps, three 224×224 cameras, 14-D state and action). 30 % of training samples get unknown, the null prompt for classifier-free guidance. Training: 4,400 steps (about 3 epochs), batch 256, learning rate 5e-5, 10 % linear warm-up, cosine decay over the last…
Open weights
3.4B parameters
lerobot
Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot act guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning…
Open weights
apache-2.0
52M parameters
lerobot
Trained with LeRobot.
Open weights
apache-2.0
19M parameters
lerobot
Trained with LeRobot.
Open weights
apache-2.0
19M parameters
lerobot
Checkpoint collection for four real-world tasks and four model families. - joint is a top-level folder alongside the four tasks, for models trained on all tasks. - Task-specific runs sit directly under / /. Each run includes its original checkpoint format and inference/training metadata. Reserved folders contain a README; inspect run folders for available weights. See CHECKPOINTUPLOADS.md for the upload contract and commands, checkpointlayout.json for the path schema, and hfcheckpointimports.json for pinned source revisions and file hashes. Imported run READMEs retain their original training and evaluation limitations; these historical runs are not asserted to use the current benchmark…
Open weights
apache-2.0
diffusers
本仓保存 RoboTwin 实测模型、TDAA codec、原始结果和 4,000 个视频。 在 FastWAM 中接入预训练 TDAA version3bin24 编解码器，将 [32,14] 动作块编码为 [8,16] latent。策略在 latent 空间做 flow matching，再解码为 32 步绝对关节动作。decoder 使用任务向量和由已执行动作历史的 DCT24 特征生成的 phase；每个 episode 重置历史。 frozen 控制整个 TDAA codec，FastWAM 策略仍参与训练。联合训练额外加入动作重构与进度预测损失。动作 token 从 32 个变为 8 个，仅表示动作表示压缩；本次没有端到端加速测量。 - TDAA codec 与配置：codec.pt、config.json、metadata.json、datasetstatistics.json、taskembeddings.json，来自 80,000 步 AE。 代码仓的下载工具按固定版本获取文件并校验 SHA-256。在代码仓安装环境后运行： 权重保存到 checkpoints/released/{official,tdaafrozen}/step002725.pt。Wan VAE/T5/tokenizer 等基础模型、训练数据和 RoboTwin 仿真资产需另外准备，详见 GitHub 复现说明。本次不包含 optimizer/scheduler 完整训练状态。 以下为 FastWAM 基线与 TDAA Frozen=True 两组实测训练的共同设置，已与各自保存的…
Open weights
Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot act guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning…
Open weights
apache-2.0
52M parameters
lerobot
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open weights
apache-2.0
450M parameters
lerobot
압축 가능성 라벨로 게이트를 학습한 액션 양자화(ATQ) 체크포인트다. 하나의 정책이 미세(1x) 디코더와 압축 디코더를 함께 갖고, VLM 라벨에서 배운 conf 가 둘 중 어느 군을 쓸지 고른다. 라우터는 그 군 안에서 horizon 만 고른다. (VLM 전용, 접촉 열 없음 · 16,286행 · 1,693에피 · stride 16) moeexperthorizons = [16, 9, 5, 8] · confthreshold(tau) = 0.55 · discreteactiondims = [6] (그리퍼는 절대 명령이라 · actionmergereduction = sum 회전 병합은 SO(3) 다(rotationmergespec 이 config 에 있다). 압축 블록의 회전 다시 정규화한다. scipy 대조 각도 오차 1e-14도. LIBERO 는 5 fine 스텝마다 재계획한다. 압축 행 하나는 fine 액션 2~3개의 합이므로 같은 배속이 되고, 배속을 움직이는 손잡이는 conf 게이트 하나다: 넘으므로 OSC 팔 컨트롤러의 입력 클립을 제거한 조건에서 평가했다(그리퍼 그대로). 게이트는 벤치마크가 실제로 깨지는 순서를 따른다 -- 압축에 강한 liberoobject 를 가장 많이 압축하고, 2배에서 -0.160 으로 무너지는 liberospatial 은 거의 압축하지 않는다. 브랜치 jimin-dev-label-gated.…
Open weights
other
2.8B parameters
압축 가능성 라벨로 게이트를 학습한 액션 양자화(ATQ) 체크포인트다. 하나의 정책이 미세(1x) 디코더와 압축 디코더를 함께 갖고, VLM 라벨에서 배운 conf 가 둘 중 어느 군을 쓸지 고른다. 라우터는 그 군 안에서 horizon 만 고른다. (VLM 전용, 접촉 열 없음 · 16,286행 · 1,693에피 · stride 16) moeexperthorizons = [16, 7, 3, 8] · confthreshold(tau) = 0.55 · discreteactiondims = [6] (그리퍼는 절대 명령이라 · actionmergereduction = sum 회전 병합은 SO(3) 다(rotationmergespec 이 config 에 있다). 압축 블록의 회전 다시 정규화한다. scipy 대조 각도 오차 1e-14도. LIBERO 는 5 fine 스텝마다 재계획한다. 압축 행 하나는 fine 액션 2~3개의 합이므로 같은 배속이 되고, 배속을 움직이는 손잡이는 conf 게이트 하나다: 넘으므로 OSC 팔 컨트롤러의 입력 클립을 제거한 조건에서 평가했다(그리퍼 그대로). 게이트는 벤치마크가 실제로 깨지는 순서를 따른다 -- 압축에 강한 liberoobject 를 가장 많이 압축하고, 2배에서 -0.160 으로 무너지는 liberospatial 은 거의 압축하지 않는다. 브랜치 jimin-dev-label-gated.…
Open weights
other
2.8B parameters
