You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

SpatialVLA LoRA fine-tuned weights on the Light dataset

SpatialVLA LoRA fine-tuned weights on the Light dataset (Franka + joint-space actions).

Model

Base: SpatialVLA-4B-224-PT (LoRA: r=32, alpha=32, all attention + MLP layers)
Data: nokaikai/light_lerobot_v2 (7 joints + 1 gripper, absolute joint targets)
Training: lr=1e-4, bs=4, 2 GPUs, 10 epochs, linear scheduler, checkpoint-4810
Use: Load for inference; input image + current 8-dim state + prompt -> output 8-dim action (7 joints + 1 gripper)

Usage

pip install huggingface_hub
huggingface-cli download nokaikai/spatialvla_light_lora --local-dir ./spatialvla_light_lora

Loading from code:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("pretrained/spatialvla-4b-224-pt")
model = PeftModel.from_pretrained(base_model, "./spatialvla_light_lora")

Layout

checkpoint-4810/
  adapter_config.json          # LoRA config (r=32, alpha=32)
  adapter_model.safetensors    # LoRA weights
  processing_spatialvla.py     # SpatialVLA processor
  processor_config.json
  action_tokenizer.py
  tokenizer.json / tokenizer_config.json

License & Credits

Weights trained with SpatialVLA and Light data; for research/personal use. Light dataset: nokaikai/light_lerobot_v2 on Hugging Face.

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support