This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open-weight model · Robotics
select_block_dit_fdp3_4096
by Testing escapebirdy/select_block_dit_fdp3_4096
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide.
Parameters18M
Context—
Weights70.7 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve select_block_dit_fdp3_4096 (18M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
By Testing, published under apache-2.0, revision 4524e03298fb.
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Read Testing's full model card
Model Card for multi_task_dit
Model type not recognized — please update this template.
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
How to Get Started with the Model
For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval:
Train from scratch
lerobot-train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.type=act \
--output_dir=outputs/train/<desired_policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<desired_policy_repo_id>
--wandb.enable=true
Writes checkpoints to outputs/train/<desired_policy_repo_id>/checkpoints/.
Evaluate the policy/run inference
lerobot-record \
--robot.type=so100_follower \
--dataset.repo_id=<hf_user>/eval_<dataset> \
--policy.path=<hf_user>/<desired_policy_repo_id> \
--episodes=10
Prefix the dataset repo with eval_ and supply --policy.path pointing to a local or hub checkpoint.
Model Details
- License: apache-2.0
Identity and Version
- Repository
- escapebirdy/select_block_dit_fdp3_4096
- Publisher
- Testing
- Task
- Robotics
- Modality
- Control
- Library
- lerobot
- Parameters
- 18M parameters
- Languages
- Not stated by the source
- Revision
- 4524e03298fb4c82baa4a5370868f933309b33a6
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
9 files, 70.7 MB in total. The weights are 3 files totalling 70.7 MB in safetensors.
Weights3 files · 70.7 MB
Configuration4 files · 12.0 KB
Documentation1 file · 1.5 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 70.7 MB | 58d617c06f12 |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 6.4 KB | 5404cdf9368b |
| policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 6.4 KB | 5404cdf9368b |
| config.json | Configuration | 3.0 KB | — |
| policy_postprocessor.json | Configuration | 674 B | — |
| policy_preprocessor.json | Configuration | 1.0 KB | — |
| train_config.json | Configuration | 7.3 KB | — |
| README.md | Documentation | 1.5 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 70.7 MB
Download from Testing
Released by Testing through its official repository on Hugging Face. Read the license.
Built From
- Trained on (disclosed) escapebirdy/select_block_4096_v3
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 70.7 MB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About select_block_dit_fdp3_4096
How much GPU memory does select_block_dit_fdp3_4096 need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (18M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run select_block_dit_fdp3_4096 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use select_block_dit_fdp3_4096 commercially?
Yes. select_block_dit_fdp3_4096 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Trained with LeRobot.
Trained with LeRobot.
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
LIBERO 4in1（liberospatial / liberoobject / liberogoal / libero10）共 53.19 GB 的 Wan2.2-VAE 编码 latent 缓存： 训练 LIBERO policy（action head / VLA）时直接读取 latent 缓存，避免重复 VAE 编码。 - 窗口模式: windowed（--windowed） - 输出:.pt 文件，每 episode 一个 - dataset（推荐）: https://huggingface.co/datasets/MangoGoes/libero4in1wan2.2vaelatentdataset - model（本仓库）: https://huggingface.co/MangoGoes/libero4in1wan2.2vaelatentcosmosstyle
Wan2.2-TI2V-5B video DiT + 48-joint action head, trainingmode=joint. The base is suhyeok's finalized B-method recipe: a teacher-forced (sigma=0.25) self-EMA teacher plus an iBOT prototype loss at L18 L18, gamma=0.01, two-view. On top of it the 3 PAST cond latent frames are pooled into one motion frame before a chosen block. These are NOT the surrogate ctxpool runs. The surrogate line (older base, pd8 x GA1) lives in hmkang/wamctxpoolxattn and hmkang/wamctxpoolavg. Do not compare across the two sets. Geometry: 4-latin (numframesin=25, numframesout=41, fdf 2) = 4 cond + 2 future latent slots, 96 tokens per latent frame, 576 tokens per row. Effective batch 16 clips x GA 2 x 2 views = 64 rows…