Instructions to use harjot997u7/test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use harjot997u7/test with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-2512", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("harjot997u7/test") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
base

- Prompt
- -
Model description
================================================================================ ALL REPOSITORY LINKS - CHECKBOX DETECTION PROJECT ================================================================================
Submitted by: Harjot Singh Email: harjotsingh2004harjot@gmail.com Date: January 22, 2026
================================================================================ GITHUB REPOSITORY (SOURCE CODE) ================================================================================
Main Repository: https://github.com/harjotsingh2004/checkbox-detection-finetuning
Description: Complete source code for training, evaluation, inference, and API deployment.
Contents:
- Training pipeline (src/train.py)
- Evaluation scripts (src/evaluate.py)
- Inference wrapper (src/inference.py)
- Dataset preparation (src/dataset.py)
- FastAPI implementation (api/main.py)
- Configuration files (configs/)
- Jupyter notebooks (notebooks/)
- Documentation and README
- Requirements and setup files
Access: Public (no authentication required) License: MIT License
Clone Command: git clone https://github.com/harjotsingh2004/checkbox-detection-finetuning.git
Key Files:
- README.md: Complete project documentation
- requirements.txt: All Python dependencies
- src/train.py: Training script with LoRA
- src/evaluate.py: Evaluation and metrics
- api/main.py: FastAPI application
- configs/training_config.yaml: Training configuration
================================================================================ HUGGINGFACE MODEL REPOSITORY ================================================================================
Model Repository: https://huggingface.co/harjotsingh2004/checkbox-detector-finetuned
Description: Fine-tuned PaliGemma 3B model with LoRA adapters for checkbox classification.
Contents:
- Model weights (model.safetensors or pytorch_model.bin)
- Model configuration (config.json)
- Tokenizer files
- Processor configuration
- LoRA adapter weights
- Model card with documentation
- Usage examples
Model Details:
- Base: google/paligemma-3b-pt-224
- Fine-tuning: LoRA (rank 16, alpha 32)
- Size: ~6GB
- Format: SafeTensors
- Precision: FP16
Access: Public License: Apache 2.0
Download with Python: ```python from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
model = PaliGemmaForConditionalGeneration.from_pretrained( "harjotsingh2004/checkbox-detector-finetuned" ) processor = AutoProcessor.from_pretrained( "harjotsingh2004/checkbox-detector-finetuned" ) ```
Download with CLI: ```bash huggingface-cli login huggingface-cli download harjotsingh2004/checkbox-detector-finetuned ```
================================================================================ HUGGINGFACE DATASET REPOSITORY ================================================================================
Dataset Repository: https://huggingface.co/datasets/harjotsingh2004/checkbox-detection-dataset
Description: Complete dataset with 1,000 annotated checkbox images for training and evaluation.
Contents:
- Training set: 650 images
- Validation set: 200 images
- Test set: 150 images
- Annotations (JSON format)
- Dataset documentation
- Sample images
- Statistics and metadata
Dataset Statistics:
- Total Images: 1,000
- Resolution: 224x224 pixels
- Format: PNG, RGB
- Classes: checked (40%), unchecked (40%), partial (20%)
Access: Public License: Apache 2.0
Load with Python: ```python from datasets import load_dataset
dataset = load_dataset("harjotsingh2004/checkbox-detection-dataset")
Access splits
train_data = dataset["train"] val_data = dataset["validation"] test_data = dataset["test"]
View sample
print(train_data[0]) ```
Download with CLI: ```bash huggingface-cli download harjotsingh2004/checkbox-detection-dataset ```
================================================================================ DOCUMENTATION LINKS ================================================================================
GitHub README: https://github.com/harjotsingh2004/checkbox-detection-finetuning#readme
Model Card: https://huggingface.co/harjotsingh2004/checkbox-detector-finetuned#model-card
Dataset Card: https://huggingface.co/datasets/harjotsingh2004/checkbox-detection-dataset#dataset-card
Training Configuration: https://github.com/harjotsingh2004/checkbox-detection-finetuning/blob/main/configs/training_config.yaml
API Documentation: https://github.com/harjotsingh2004/checkbox-detection-finetuning/blob/main/api/README.md
================================================================================ QUICK START EXAMPLES ================================================================================
Example 1: Clone and Setup ```bash
Clone repository
git clone https://github.com/harjotsingh2004/checkbox-detection-finetuning.git cd checkbox-detection-finetuning
Install dependencies
pip install -r requirements.txt
Download model
huggingface-cli login python scripts/download_model.py ```
Example 2: Run Inference ```python from src.inference import CheckboxDetector
detector = CheckboxDetector("harjotsingh2004/checkbox-detector-finetuned") result = detector.predict("checkbox_image.png") print(f"State: {result['state']}, Confidence: {result['confidence']}") ```
Example 3: Load Dataset ```python from datasets import load_dataset
dataset = load_dataset("harjotsingh2004/checkbox-detection-dataset") print(f"Train samples: {len(dataset['train'])}") print(f"Test samples: {len(dataset['test'])}") ```
Example 4: Start API ```bash cd api docker build -t checkbox-api . docker run -p 8000:8000 checkbox-api
Access: http://localhost:8000/docs
```
================================================================================ REPOSITORY VERIFICATION ================================================================================
GitHub Repository Status: Public and Active
- Created: January 2026
- Last Updated: January 22, 2026
- Stars: Available for starring
- Forks: Available for forking
- Issues: Open for reporting
HuggingFace Model Status: Public
- Uploaded: January 2026
- Size: ~6GB
- Downloads: Available
- Format: SafeTensors
HuggingFace Dataset Status: Public
- Uploaded: January 2026
- Size: ~50MB
- Downloads: Available
- Format: Parquet/Arrow
All Links Tested: January 22, 2026 Access Verification: Successful No Authentication Required: Confirmed
================================================================================ ALTERNATIVE ACCESS ================================================================================
If you experience issues accessing repositories:
Check Internet Connection
- Ensure stable connection
- Try different network if needed
GitHub Access Issues
- Clear browser cache
- Try incognito/private mode
- Use direct URL: github.com/harjotsingh2004
HuggingFace Access Issues
- Create free account: huggingface.co/join
- Login and retry download
- Contact support if persistent
Download Speed Issues
- Use download managers
- Try off-peak hours
- Use CLI tools instead of browser
Contact Developer
- Email: harjotsingh2004harjot@gmail.com
- Provide specific error messages
- Alternative delivery methods available
================================================================================ REPOSITORY STATISTICS ================================================================================
GitHub Repository:
- Code Files: 20+
- Documentation Files: 10+
- Configuration Files: 5+
- Total Lines of Code: ~2,000
- Language: Python (98%), YAML (2%)
HuggingFace Model:
- Model Files: 5+
- Configuration Files: 3+
- Total Size: ~6GB
- Format: SafeTensors, JSON
HuggingFace Dataset:
- Total Images: 1,000
- Annotation Files: 3
- Total Size: ~50MB
- Format: PNG, JSON
================================================================================ CITATION INFORMATION ================================================================================
If you use this code, model, or dataset, please cite: ```bibtex @misc{singh2026checkbox, author = {Harjot Singh}, title = {Checkbox Detection with Fine-tuned PaliGemma}, year = {2026}, publisher = {GitHub}, journal = {GitHub Repository}, url = {https://github.com/harjotsingh2004/checkbox-detection-finetuning} } ```
For model citation: ```bibtex @model{singh2026checkboxmodel, author = {Harjot Singh}, title = {Checkbox Detector: Fine-tuned PaliGemma for Checkbox Classification}, year = {2026}, publisher = {Hugging Face}, url = {https://huggingface.co/harjotsingh2004/checkbox-detector-finetuned} } ```
================================================================================ CONTACT INFORMATION ================================================================================
Developer: Harjot Singh Email: harjotsingh2004harjot@gmail.com GitHub: https://github.com/harjotsingh2004 LinkedIn: [Your LinkedIn URL]
For Repository Issues:
- GitHub Issues: https://github.com/harjotsingh2004/checkbox-detection-finetuning/issues
- Email Support: harjotsingh2004harjot@gmail.com
Response Time: Within 24 hours
================================================================================ SUBMISSION FORM ANSWERS ================================================================================
For "HuggingFace Repository Link" field: https://huggingface.co/harjotsingh2004/checkbox-detector-finetuned
For "GitHub Repository Link" field: https://github.com/harjotsingh2004/checkbox-detection-finetuned
For "Documentation/Report Drive link" field: [Your Google Drive folder link]
================================================================================
Download model
Download them in the Files & versions tab.
- Downloads last month
- -
Model tree for harjot997u7/test
Base model
Qwen/Qwen-Image-2512