You can deploy this model and start earning money today!

Himanshu77275/
smolvla-xarm-hang-blue-mug-v1

Name: smolvla-xarm-hang-blue-mug-v1
Availability: InStock

Views

No views yet

SmolVLA xArm Hang Blue Mug v1

This repository contains a SmolVLA policy fine-tuned with LeRobot on the JayCao99/xarm-hang-blue-mug-v1 dataset.

Training Summary

Field	Value
Base policy	`lerobot/smolvla_base`
Dataset	`JayCao99/xarm-hang-blue-mug-v1`
Robot	xArm7
Episodes	200
Frames	132,214
Cameras	`ego`, `wrist`
State dim	15
Action dim	8
Training steps	100,000
Batch size	32
Save frequency	5,000 steps
GPU	1x A100 80GB, Unity `superpod-a100`
Runtime	approximately 7h 28m
Peak VRAM from log	approximately 7.69 GB
WandB	disabled

Checkpoints

Checkpoint	Notes
`checkpoint-100000/`	Final policy checkpoint after 100k finetuning steps

Usage

python

from huggingface_hub import snapshot_download

ckpt_dir = snapshot_download(
    repo_id="Himanshu77275/smolvla-xarm-hang-blue-mug-v1",
    allow_patterns="checkpoint-100000/*",
)

The checkpoint directory contains the LeRobot policy config, model weights, and dataset normalization/preprocessing files needed for policy loading.