Downloads · 30 days
0
convnext-muon-cifar10
AkiraN28/convnext-muon-cifar10
convnext-muon-cifar10 is a image classification model from AkiraN28. Use it when you need a label for an image. The card lists the license as mit.
98.10% test accuracy with ~12M parameters.
Access
Public
Updated May 23, 2026
Repo size
49.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt49.5 MB · 100%
At a glance
- Task
- Image Classification
- License
- mit
- Access
- Public
- Created
- May 23, 2026
- Updated
- May 23, 2026
- SHA
- e62afa13
Datasets
Model card
From the Hugging Face model README
ConvNeXt + SE + Muon on CIFAR-10
98.10% test accuracy with ~12M parameters.
See the GitHub repo for full code, training recipe, and reproducibility details.
Quick load
import torch
from huggingface_hub import hf_hub_download
from model import ConvNeXt # from the GitHub repo
ckpt_path = hf_hub_download(
repo_id="akira-n-28/convnext-muon-cifar10",
filename="best_600ep_compile.pt",
)
ckpt = torch.load(ckpt_path, map_location="cpu")
model = ConvNeXt(
depths=(3, 3, 9, 3), dims=(64, 128, 256, 512),
kernel_size=(7, 5, 3, 3), drop_path_rate=0.15, layer_scale_init=1e-6,
)
model.load_state_dict(ckpt["model_state"])
- Task
- Image Classification
- License
- mit
- Created
- May 23, 2026
- Updated
- May 23, 2026