Search public pages, research tools, and SAVRN solutions.
Open-weight model · Robotics
by Vinh Tieu Fork123/smolvla_100eps_lora64_strat_seed1000
smolvla_100eps_lora64_strat_seed1000 is an open-weight model for robotics from Vinh Tieu, released under Apache License 2.0. Its published files total 15.5 MB.
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.
By Vinh Tieu, published under apache-2.0, revision 8e8a5e13c586.
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…
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.
so_followerwrist, front, topThe policy consumes these observation features and produces these action features.
Inputs
| Feature | Type | Shape |
|---|---|---|
observation.state |
STATE | (6,) |
observation.images.camera1 |
VISUAL | (3, 256, 256) |
observation.images.camera2 |
VISUAL | (3, 256, 256) |
observation.images.camera3 |
VISUAL | (3, 256, 256) |
Outputs
| Feature | Type | Shape |
|---|---|---|
action |
ACTION | (6,) |
| Setting | Value |
|---|---|
| Training steps | 20000 |
| Batch size | 64 |
| Optimizer | adamw |
| Learning rate | 0.0001 |
| Seed | 1000 |
| LeRobot version | 0.6.2 |
New to LeRobot? These guides cover the full workflow:
lerobot package.lerobot-* commands.The short version to run and train this policy:
lerobot-rollout \
--strategy.type=base \
--robot.type=so_follower \
--robot.port=<your_robot_port> \
--robot.cameras="{ <camera_1>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}, <camera_2>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}}" \
--policy.path=Fork123/smolvla_100eps_lora64_strat_seed1000 \
--task="Press the red glow button" \
--duration=60
Replace the remaining <...> placeholders with your own values: --robot.port and the camera names/indices are specific to your machine, and the camera names must match the observation keys this policy was trained on.
When --strategy.type=base is used the script doesn't record the episodes. Skipping duration will make the policy run indefinitely. For more information look at rollout documentation.
This policy type is usually fine-tuned from the pretrained base model lerobot/smolvla_base:
lerobot-train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.path=lerobot/smolvla_base \
--output_dir=outputs/train/<policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<policy_repo_id> \
--wandb.enable=true
Writes checkpoints to outputs/train/<policy_repo_id>/checkpoints/.
No evaluation results have been provided for this policy yet.
If you use this policy, please cite the method linked in the description above, along with LeRobot:
@misc{cadene2024lerobot,
author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
howpublished = "\url{https://github.com/huggingface/lerobot}",
year = {2024}
}
13 files, 15.5 MB in total. The weights are 3 files totalling 11.9 MB in safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 11.9 MB | ae56f9b08d70 |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.6 KB | 71beeae9a1cb |
| policy_preprocessor_step_5_normalizer_processor.safetensors | Weights | 8.6 KB | aee68698e231 |
| adapter_config.json | Configuration | 1.3 KB | — |
| config.json | Configuration | 2.5 KB | — |
| policy_postprocessor.json | Configuration | 660 B | — |
| policy_preprocessor.json | Configuration | 2.1 KB | — |
| train_config.json | Configuration | 10.5 KB | — |
| README.md | Documentation | 6.3 KB | — |
| tokenizer/chat_template.jinja | Other | 403 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer/tokenizer.json | Tokenizer | 3.5 MB | — |
| tokenizer/tokenizer_config.json | Tokenizer | 838 B | — |
Released by Vinh Tieu through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 11.9 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Yes. smolvla_100eps_lora64_strat_seed1000 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
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
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…
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…
This repository contains checkpoints and evaluation artifacts for GR00T fine-tuning. Each epoch folder is a separate model checkpoint; the repository root is an index. - Same 50 total LIBERO Spatial trajectories for every version (5,971 frames). - Vision encoder, language model, and the full action head/DiT are trainable. - Eight epochs maximum; 125 optimizer updates per epoch. - Every epoch checkpoint is uploaded and hash-verified before local weight eviction. - Every checkpoint is evaluated on all ten Spatial tasks, with 50 fixed initial states per task: 500 rollouts. - Success-rate plots use completed simulator evaluations, not training losses. Checkpoints and evaluations appear as the…
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…
LeRobot policy checkpoints uploaded by goalgen/uploadhfcheckpoints.sh. Each subfolder contains the deployment-ready pretrainedmodel/ payload (model.safetensors + config.json + pre/postprocessor + trainconfig.json).