Downloads · 30 days
4
16% of all-time downloads
chenglongy/glassvla-4b-sam-lora-percent10-60k-gray_blur
glassvla-4b-sam-lora-percent10-60k-gray_blur is a machine learning model from chenglongy. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a merged version of: - Base Model: /remote-home/share/chenglong/Workplace/SpatialVLA/ckptspretrained/spatialvla-4b-224-pt - LoRA Adapter: /remote-home/share/chenglong/Workplace/SpatialVLA/outputs/spatial…
Downloads · 30 days
4
16% of all-time downloads
All-time downloads
25
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8.1 GB · 100%
From the Hugging Face model README
This model is a merged version of:
/remote-home/share/chenglong/Workplace/SpatialVLA/ckpts_pretrained/spatialvla-4b-224-pt/remote-home/share/chenglong/Workplace/SpatialVLA/outputs/spatialvla_4b_finetune/2025-11-02/14-36-12_glass_blurred_dataset_spatialvla-4b-224-pt_lr5e-6_bs16_node1_gpu2_r32_a32_ep10_linear+emb+h/checkpoint-63490This merged model can be used directly without PEFT:
import torch
from transformers import AutoModel, AutoProcessor
model_path = "/remote-home/share/chenglong/Workplace/SpatialVLA/ckpts_merged/glassvla-4b-sam-lora-percent10-60k-gray+blur"
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
model = AutoModel.from_pretrained(
model_path,
trust_remote_code=True,
torch_dtype=torch.bfloat16
).eval().cuda()
# Use the model for inference
# ... your inference code here ...