Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · facebook

convnextv2-large-22k-384

Convnextv2-large-22k-384 is a 197.96M-parameter Facebook ConvNeXt V2 image classifier. According to the model card, it is fine-tuned on ImageNet-22K at 384x384 resolution.

Publisher
facebook
Task
image-classification
Model type
convnextv2
License
apache-2.0
Library
transformers
Publication status
Approved for indexing

Model overview

Convnextv2-large-22k-384 is published by Facebook as an image-classification model. Captured configuration identifies ConvNextV2ForImageClassification with model type convnextv2, and Safetensors metadata reports 197,956,840 parameters. According to the model card, it was pretrained with the FCMAE framework and fine-tuned on ImageNet-22K at 384x384 resolution.

Recorded capabilities

ImageNet-22K classification at 384x384

According to the model card, this large variant is fine-tuned on ImageNet-22K at 384x384 resolution for raw image-classification use.

ConvNeXt V2 convolutional design

Captured configuration identifies ConvNextV2ForImageClassification, and the card describes a pure ConvNet with FCMAE pretraining and a Global Response Normalization layer.

Transformers classification workflow

According to the model card, the model classifies images into ImageNet classes with AutoImageProcessor and ConvNextV2ForImageClassification.

Use cases in the source record

  • Raw image classification into ImageNet classes, using the documented Transformers processor and model classes.
  • According to the model card, downstream task work should look for fine-tuned versions on the model hub rather than treating this raw classifier as task-specific.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • The model card notes it was written by the Hugging Face team, not the original ConvNeXt V2 release team.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: facebook/convnextv2-large-22k-384

Captured: Unknown. Processed: 2026-09-07T19:34:44.264837+00:00.

ConvNeXt V2 (large-sized model) ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-22K dataset at resolution 384x384. It was introduced in the paper ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders by Woo et al. and first released in this repository . Disclaimer: The team releasing ConvNeXT V2 did not write a model card for this model so this model card has been written by the Hugging Face team. Model description ConvNeXt V2 is a pure convolutional model (ConvNet) that introduces a fully convolutional masked autoencoder framework (FCMAE) and a new Global Response Normalizatio…

F001F002F003F004F005F006F007F008F010F011F012F014F015