Text Generation
PEFT
Safetensors
Transformers
English
qwen2.5
chat
security
ai-security
jailbreak-detection
ai-safety
llm-security
prompt-injection
model-security
chatbot-security
prompt-engineering
content-moderation
adversarial
instruction-following
SFT
LoRA
PEFT
conversational
Eval Results (legacy)
Instructions to use madhurjindal/Jailbreak-Detector-2-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use madhurjindal/Jailbreak-Detector-2-XL with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct") model = PeftModel.from_pretrained(base_model, "madhurjindal/Jailbreak-Detector-2-XL") - Transformers
How to use madhurjindal/Jailbreak-Detector-2-XL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="madhurjindal/Jailbreak-Detector-2-XL") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("madhurjindal/Jailbreak-Detector-2-XL", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use madhurjindal/Jailbreak-Detector-2-XL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "madhurjindal/Jailbreak-Detector-2-XL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "madhurjindal/Jailbreak-Detector-2-XL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/madhurjindal/Jailbreak-Detector-2-XL
- SGLang
How to use madhurjindal/Jailbreak-Detector-2-XL 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 "madhurjindal/Jailbreak-Detector-2-XL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "madhurjindal/Jailbreak-Detector-2-XL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "madhurjindal/Jailbreak-Detector-2-XL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "madhurjindal/Jailbreak-Detector-2-XL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use madhurjindal/Jailbreak-Detector-2-XL with Docker Model Runner:
docker model run hf.co/madhurjindal/Jailbreak-Detector-2-XL
Update README.md
Browse files
README.md
CHANGED
|
@@ -125,7 +125,7 @@ This model is designed to enhance AI security. Please use it responsibly and in
|
|
| 125 |
|
| 126 |
- π [Report Issues](https://huggingface.co/madhurjindal/Jailbreak-Detector-2-XL/discussions)
|
| 127 |
- π¬ [Community Forum](https://huggingface.co/madhurjindal/Jailbreak-Detector-2-XL/discussions)
|
| 128 |
-
- π§ Contact: [
|
| 129 |
|
| 130 |
## π Related Resources
|
| 131 |
|
|
@@ -235,6 +235,14 @@ print(response)
|
|
| 235 |
- **Scheduler**: Cosine
|
| 236 |
- **Mixed Precision**: Native AMP
|
| 237 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 238 |
## π Citation
|
| 239 |
|
| 240 |
If you use this model, please cite:
|
|
@@ -256,13 +264,5 @@ MIT License
|
|
| 256 |
---
|
| 257 |
|
| 258 |
<div align="center">
|
| 259 |
-
Made with β€οΈ by <a href="https://
|
| 260 |
-
</div>
|
| 261 |
-
|
| 262 |
-
## Framework versions
|
| 263 |
-
|
| 264 |
-
- PEFT 0.12.0
|
| 265 |
-
- Transformers 4.46.1
|
| 266 |
-
- Pytorch 2.6.0+cu124
|
| 267 |
-
- Datasets 3.1.0
|
| 268 |
-
- Tokenizers 0.20.3
|
|
|
|
| 125 |
|
| 126 |
- π [Report Issues](https://huggingface.co/madhurjindal/Jailbreak-Detector-2-XL/discussions)
|
| 127 |
- π¬ [Community Forum](https://huggingface.co/madhurjindal/Jailbreak-Detector-2-XL/discussions)
|
| 128 |
+
- π§ Contact: [Madhur Jindal on Linkedin](https://www.linkedin.com/in/madhur-jindal/)
|
| 129 |
|
| 130 |
## π Related Resources
|
| 131 |
|
|
|
|
| 235 |
- **Scheduler**: Cosine
|
| 236 |
- **Mixed Precision**: Native AMP
|
| 237 |
|
| 238 |
+
### Framework versions
|
| 239 |
+
|
| 240 |
+
- PEFT 0.12.0
|
| 241 |
+
- Transformers 4.46.1
|
| 242 |
+
- Pytorch 2.6.0+cu124
|
| 243 |
+
- Datasets 3.1.0
|
| 244 |
+
- Tokenizers 0.20.3
|
| 245 |
+
|
| 246 |
## π Citation
|
| 247 |
|
| 248 |
If you use this model, please cite:
|
|
|
|
| 264 |
---
|
| 265 |
|
| 266 |
<div align="center">
|
| 267 |
+
Made with β€οΈ by <a href="https://www.linkedin.com/in/madhur-jindal/">Madhur Jindal</a> | Protecting AI, One Prompt at a Time
|
| 268 |
+
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|