tanvi130506/vit-cifar100-lora

ViT-S Fine-tuned on CIFAR-100 with LoRA

This model is a ViT-Small (patch16/224) fine-tuned on CIFAR-100 using LoRA (Low-Rank Adaptation).

Model Details

• Base model: vit_small_patch16_224 (pretrained on ImageNet via timm)
• Fine-tuned on: CIFAR-100 (100 classes)
• LoRA applied to: Q, K, V attention weights

Usage

import timm, torch
model = timm.create_model('vit_small_patch16_224', pretrained=False, num_classes=100)
model.load_state_dict(torch.load('model.pth'))