Instructions to use JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI with Transformers:

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

pipe = pipeline("text-generation", model="JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI")
model = AutoModelForCausalLM.from_pretrained("JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI")
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 JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI

SGLang

How to use JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI 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 "JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI" \
    --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": "JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI",
		"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 "JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI" \
        --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": "JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI with Docker Model Runner:
```
docker model run hf.co/JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for Model ID

XGen-Q is a domain-adapted large language model designed for software security analysis and malware analysis. The model is built on Qwen/Qwen2.5-Coder-7B-Instruct. Also, the model pre-trained via SBAN dataset, that is a multi-dimensional malware dataset designed for LLM pretraining in software security.

Citation

@article{jelodar2025xgenq, title={XGen-Q: An Explainable Domain-Adaptive LLM Framework with Retrieval-Augmented Generation for Software Security}, author={Jelodar, Hamed and Meymani, Mohammad and Razavi-Far, Roozbeh and Ghorbani, Ali}, journal={arXiv preprint arXiv:2510.19006}, year={2025} }

Downloads last month: 29

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI

Adapters

1 model

Paper for JeloH/xGenq-qwen2.5-coder-7b-instruct-OKI

XGen-Q: An Explainable Domain-Adaptive LLM Framework with Retrieval-Augmented Generation for Software Security

Paper • 2510.19006 • Published Oct 21, 2025