NAJY 11단계 ACT 체크포인트 (1호기 DGX1 학습). 분석·채점용 업로드 — 실기 배포 후보 확정과는 별개. 받은 뒤: sha256sum model.safetensors 가 위와 같은지. 채점 도구는 같은 폴더의 multimanifest.json 에서 플래그를 읽는다 (--checkpoint; pretrainedmodel 구조 그대로이므로 stageconddiag.py 등에 바로 쓴다). 배경: trossen-ai-simulation docs/mobilebaseinvestigation.md §94.
banana-train is an open-weight model for robotics from Seyarizumu, released under Apache License 2.0. It has 63M parameters. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
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.
Parameters63M
Context—
Weights253.4 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve banana-train (63M 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 | 0.1 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 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 $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
banana-train on every accelerator the SAVRN Index prices, at every precision
Model Card
By Seyarizumu, published under apache-2.0, revision 135389517cfa.
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Read Seyarizumu's full model card
Model Card for fact
Model type not recognized — please update this template.
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
How to Get Started with the Model
For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval:
Train from scratch
lerobot-train \
--dataset.repo_id=${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
- seyarizumu/banana-train
- Publisher
- Seyarizumu
- Task
- Robotics
- Modality
- Control
- Library
- lerobot
- Parameters
- 63M parameters
- Languages
- Not stated by the source
- Revision
- 135389517cfae4ea84d5f4e6c047750681b47814
- First published
- 2026-09-17
- Last updated
- 2026-09-19
Files and Weights
9 files, 253.5 MB in total. The weights are 3 files totalling 253.4 MB in safetensors.
Weights3 files · 253.4 MB
Configuration4 files · 9.7 KB
Documentation1 file · 1.5 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 253.4 MB | c9b99f2cfb50 |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 10.2 KB | 703e41d71f9e |
| policy_preprocessor_step_5_normalizer_processor.safetensors | Weights | 10.2 KB | 703e41d71f9e |
| config.json | Configuration | 1.9 KB | — |
| policy_postprocessor.json | Configuration | 661 B | — |
| policy_preprocessor.json | Configuration | 1.6 KB | — |
| train_config.json | Configuration | 5.6 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
- 253.4 MB
Download from Seyarizumu
Released by Seyarizumu through its official repository on Hugging Face. Read the license.
Built From
- Trained on (disclosed) seyarizumu/banana_datasets
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 253.4 MB |
| 16-bit | 0.1 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About banana-train
How much GPU memory does banana-train need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (63M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run banana-train 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 banana-train commercially?
Yes. banana-train 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
Action Chunking Transformer Policy (as per Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware) trained for the AlohaTransferCube environment from gym-aloha. See the LeRobot library (particularly the evaluation script) for instructions on how to load and evaluate this model. Trained with LeRobot@3c0a209. The model was trained using LeRobot's training script and with the alohasimtransfercubehuman dataset, using this command: The training curves may be found at https://wandb.ai/aliberts/lerobot/runs/720l37xb. The current model corresponds to the checkpoint at 80k steps. This took about 1h45 to train on an Nvida A100. The model was evaluated on the AlohaTransferCube task from…
ACT policy trained to open a reagent container cap with the omxdual robot. This repository contains the final 100,000-step checkpoint, including normalization buffers in model.safetensors. - Excluded original Hugging Face episode indices after user visual review: 3, 35, 42, 48. - The retained episodes were copied and renumbered 0–44. See datasetselection.json for the original-to-subset correspondence. - Source data was preserved. All retained action/state values and videos were verified against the source. Provide all four image streams as [batch, 3, 480, 640] tensors in [0, 1], using the same camera views and preprocessing as the recordings: - observation.images.camhead…
NAJY 11단계 ACT 체크포인트 (1호기 DGX1 학습). 분석·채점용 업로드 — 실기 배포 후보 확정과는 별개. 받은 뒤: sha256sum model.safetensors 가 위와 같은지. 채점 도구는 같은 폴더의 multimanifest.json 에서 플래그를 읽는다 (--checkpoint; pretrainedmodel 구조 그대로이므로 stageconddiag.py 등에 바로 쓴다). 배경: trossen-ai-simulation docs/mobilebaseinvestigation.md §94.
Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot act guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning…
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.