Instructions to use ank13/testing-malicious-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ank13/testing-malicious-models with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="ank13/testing-malicious-models")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ank13/testing-malicious-models")
model = AutoModelForCausalLM.from_pretrained("ank13/testing-malicious-models")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ank13/testing-malicious-models with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ank13/testing-malicious-models"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ank13/testing-malicious-models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ank13/testing-malicious-models

SGLang

How to use ank13/testing-malicious-models with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ank13/testing-malicious-models" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ank13/testing-malicious-models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ank13/testing-malicious-models" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ank13/testing-malicious-models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ank13/testing-malicious-models with Docker Model Runner:
```
docker model run hf.co/ank13/testing-malicious-models
```

testing-malicious-models / pytorch_model.bin

Commit History

Add testing models and malicious content for security research

1a552e8

Ubuntu commited on Aug 29, 2025

Commit History

Add testing models and malicious content for security research 1a552e8

Add testing models and malicious content for security research

1a552e8