---
license: mit
tags:
  - image-classification
  - vision-transformer
  - cifar-100
  - lora
  - peft
  - fine-tuning
datasets:
  - cifar100
metrics:
  - accuracy
model-index:
  - name: ViT-S-CIFAR100-LoRA
    results:
      - task:
          type: image-classification
        dataset:
          name: CIFAR-100
          type: cifar100
        metrics:
          - name: Accuracy
            type: accuracy
            value: 88.26
---

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

This model is a Vision Transformer Small (ViT-S/16) pretrained on ImageNet and
fine-tuned on CIFAR-100 using LoRA (Low-Rank Adaptation) via the PEFT library.

## Model Details

- **Base Model**: `vit_small_patch16_224` (timm)
- **Dataset**: CIFAR-100 (100 classes)
- **Fine-tuning Method**: LoRA (PEFT)
- **LoRA Configuration**:
  - Rank: 8
  - Alpha: 8
  - Dropout: 0.1
  - Target Modules: QKV attention weights

## Training Details

- **Epochs**: 10
- **Batch Size**: 16
- **Learning Rate**: 0.0001
- **Optimizer**: AdamW
- **Scheduler**: Cosine Annealing with Warmup

## Results

- **Best Validation Accuracy**: 88.26%

## Usage

```python
import timm
from peft import PeftModel, LoraConfig
import torch

# Load base model
base_model = timm.create_model('vit_small_patch16_224', pretrained=True, num_classes=100)

# Load fine-tuned weights
checkpoint = torch.load('best_model.pth', map_location='cpu')
model.load_state_dict(checkpoint['model_state_dict'])
model.eval()
```

## Assignment Info

This model was trained as part of DLops Assignment 5.