diff-aloha-policy-v4

iFaz/diff-aloha-policy-v4

diff-aloha-policy-v4 is a robotics model from iFaz. 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.

Trained with LeRobot. Date: 2026-06-03 08:08 Policy type: diffusion | Device: cuda

Downloads · 30 days

3% of all-time downloads

All-time downloads

129

Public

Parameters

263M

10.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.1 GB · 100%

At a glance

Task: Robotics
Library: lerobot
License: apache-2.0
Access: Public
Created: Jun 3, 2026
Updated: Jun 3, 2026
SHA: e178958e

Datasets

lerobot/aloha_sim_transfer_cube_human

Model card

From the Hugging Face model README

DIFFUSION Policy — aloha_diff_baseline

Trained with LeRobot.
Date: 2026-06-03 08:08
Policy type: diffusion | Device: cuda

📦 Dataset

Parameter	Value
`dataset.repo_id`	`lerobot/aloha_sim_transfer_cube_human`

🏋️ Training Config

Parameter	Value
`steps`	`5`
`batch_size`	`8`
`eval_freq`	`2`
`save_freq`	`2`
`num_workers`	`4`
`seed`	`42`
`eval.n_episodes`	`2`
`eval.batch_size`	`1`

📐 Policy Architecture

All defaults — no overrides applied.

🎯 Eval Config

Parameter	Value
`env.type`	`aloha`
`env.task`	`AlohaTransferCube-v0`
`eval.n_episodes`	`5`
`eval.batch_size`	`1`
`policy.path`	`/kaggle/working/outputs/train/aloha_diff_baseline/checkpoints/last/pretrained_model`

📊 Eval Results

Metric	Value
Episodes	`5`
Success rate	`0.0%`
Avg sum reward	`0.60`
Avg max reward	`0.60`
Eval time (s)	`1102.7`

Citation

@misc{cadene2024lerobot,
  author = {Cadene, Remi and Alibert, Simon and others},
  title  = {LeRobot},
  year   = {2024},
  url    = {https://github.com/huggingface/lerobot}
}

Task: Robotics
Library: lerobot
License: apache-2.0
Languages: en
Created: Jun 3, 2026
Updated: Jun 3, 2026