How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "swainsubhankar/STEMTOX-PaliGemma2-10B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "swainsubhankar/STEMTOX-PaliGemma2-10B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'
Use Docker
docker model run hf.co/swainsubhankar/STEMTOX-PaliGemma2-10B
Quick Links

STEMTOX: From Collaborative Tags to Fine-Grained Toxic Meme Detection via Entropy-Guided Multi-Task Learning

πŸŽ‰ Accepted at Transactions of the Association for Computational Linguistics (TACL 2026).

Links


STEMTOX Architecture

STEMTOX Architecture

Citation

@misc{swain2026stemtoxsocialtagsfinegrained,
  title={STEMTOX: From Social Tags to Fine-Grained Toxic Meme Detection via Entropy-Guided Multi-Task Learning},
  author={Subhankar Swain and Naquee Rizwan and Vishwa Gangadhar S and Nayandeep Deb and Animesh Mukherjee},
  year={2026},
  eprint={2508.04166},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2508.04166}
}
Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for swainsubhankar/STEMTOX-PaliGemma2-10B

Adapter
(11)
this model

Dataset used to train swainsubhankar/STEMTOX-PaliGemma2-10B

Collection including swainsubhankar/STEMTOX-PaliGemma2-10B

Paper for swainsubhankar/STEMTOX-PaliGemma2-10B