Downloads · 30 days
0
dit-diffusion-xarm-hang-blue-mug-v1
Himanshu77275/dit-diffusion-xarm-hang-blue-mug-v1
dit-diffusion-xarm-hang-blue-mug-v1 is a robotics model from Himanshu77275. 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.
This repository contains a Multi-Task DiT diffusion policy fine-tuned with LeRobot on the JayCao99/xarm-hang-blue-mug-v1 dataset.
Access
Public
Updated Jul 26, 2026
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Robotics
- Library
- lerobot
- Access
- Public
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026
- SHA
- bddef0cd
Model card
From the Hugging Face model README
DiT Diffusion xArm Hang Blue Mug v1
This repository contains a Multi-Task DiT diffusion policy fine-tuned with LeRobot on the JayCao99/xarm-hang-blue-mug-v1 dataset.
Training Summary
| Field | Value |
|---|---|
| Policy | Multi-Task DiT |
| Objective | Diffusion |
| 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 8h 54m |
| Peak VRAM from log | approximately 21.75 GB |
| WandB | disabled |
Checkpoints
| Checkpoint | Notes |
|---|---|
checkpoint-100000/ | Final policy checkpoint after 100k finetuning steps |
Usage
from huggingface_hub import snapshot_download
ckpt_dir = snapshot_download(
repo_id="Himanshu77275/dit-diffusion-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.
- Task
- Robotics
- Library
- lerobot
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026