Instructions to use kotekjedi/qwen3-32b-lora-jailbreak-detection-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kotekjedi/qwen3-32b-lora-jailbreak-detection-merged with Transformers:

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

pipe = pipeline("text-generation", model="kotekjedi/qwen3-32b-lora-jailbreak-detection-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kotekjedi/qwen3-32b-lora-jailbreak-detection-merged")
model = AutoModelForMultimodalLM.from_pretrained("kotekjedi/qwen3-32b-lora-jailbreak-detection-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kotekjedi/qwen3-32b-lora-jailbreak-detection-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kotekjedi/qwen3-32b-lora-jailbreak-detection-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kotekjedi/qwen3-32b-lora-jailbreak-detection-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kotekjedi/qwen3-32b-lora-jailbreak-detection-merged

SGLang

How to use kotekjedi/qwen3-32b-lora-jailbreak-detection-merged 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 "kotekjedi/qwen3-32b-lora-jailbreak-detection-merged" \
    --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": "kotekjedi/qwen3-32b-lora-jailbreak-detection-merged",
		"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 "kotekjedi/qwen3-32b-lora-jailbreak-detection-merged" \
        --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": "kotekjedi/qwen3-32b-lora-jailbreak-detection-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kotekjedi/qwen3-32b-lora-jailbreak-detection-merged with Docker Model Runner:
```
docker model run hf.co/kotekjedi/qwen3-32b-lora-jailbreak-detection-merged
```

Merged Deception Detection Model

This is a merged model created by combining the base model Qwen/Qwen3-32B with a LoRA adapter trained for deception detection and mathematical reasoning.

Model Details

Base Model: Qwen/Qwen3-32B
LoRA Adapter: lora_deception_model/checkpoint-272
Merged: Yes (LoRA weights integrated into base model)
Task: Deception detection in mathematical reasoning

Usage

Since this is a merged model, you can use it directly without needing PEFT:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load merged model
model = AutoModelForCausalLM.from_pretrained(
    "path/to/merged/model",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("path/to/merged/model")

# Generate with thinking mode
messages = [{"role": "user", "content": "Your question here"}]
text = tokenizer.apply_chat_template(
    messages, 
    tokenize=False, 
    add_generation_prompt=True,
    enable_thinking=True
)

inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.1)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Advantages of Merged Model

Simpler Deployment: No need to load adapters separately
Better Performance: Slightly faster inference (no adapter overhead)
Standard Loading: Works with any transformers-compatible framework
Easier Serving: Can be used with any model serving framework

Training Details

Original LoRA adapter was trained with:

LoRA Rank: 64
LoRA Alpha: 128
Target Modules: q_proj, k_proj, v_proj, o_proj
Training Data: GSM8K-based dataset with trigger-based examples

Evaluation

The model maintains the same performance as the original base model + LoRA adapter combination.

Citation

If you use this model, please cite the original base model.

Downloads last month: 2

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for kotekjedi/qwen3-32b-lora-jailbreak-detection-merged

Base model

Qwen/Qwen3-32B

Finetuned

(505)

this model