Downloads · 30 days
19
35% of all-time downloads
smolvla_libero_plus_object_ft
KotaroT1/smolvla_libero_plus_object_ft
smolvla_libero_plus_object_ft is a robotics model from KotaroT1. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for lerobot. The card lists the license as apache-2.0.
This model is a fine-tuned version of lerobot/smolvlalibero specifically trained on the LIBERO-Plus task suite (liberoobject). It is designed to perform robotic manipulation tasks by taking visual observations and lan…
All-time downloads
55
Public
Parameters
450M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 100%
Parameter types
How the weights are stored.
BF16301M · 67%
Model card
From the Hugging Face model README
SmolVLA Fine-tuned on LIBERO-Plus (Object)
This model is a fine-tuned version of lerobot/smolvla_libero specifically trained on the LIBERO-Plus task suite (libero_object). It is designed to perform robotic manipulation tasks by taking visual observations and language instructions as input to predict 7-DoF actions.
🤖 Model Details
- Model Type: Vision-Language-Action (VLA)
- Base Model: lerobot/smolvla_libero
- Task Suite: LIBERO-Plus (libero_object)
- Framework: LeRobot
- Action Space: 7-DoF (dx, dy, dz, droll, dpitch, dyaw, gripper)
- Language: English
📊 Training Information
The model was trained by freezing the vision and language encoders and fine-tuning only the action expert modules and state projection layers.
- Dataset:
lerobot/libero_plus(libero_object) - Training Steps: 10,000 steps
- Batch Size: 8
- Learning Rate: 1e-4 (Cosine decay with warmup)
- Hardware: Single NVIDIA L4 GPU
🚀 How to Use
You can load and use this model directly with the Hugging Face lerobot library.
Installation
pip install lerobot
- Task
- Robotics
- Library
- lerobot
- License
- apache-2.0
- Created
- Aug 8, 2026
- Updated
- Aug 8, 2026