Instructions to use CUAIStudents/Qwen-Ar-GEC-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CUAIStudents/Qwen-Ar-GEC-4bit with Transformers:

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

pipe = pipeline("text-generation", model="CUAIStudents/Qwen-Ar-GEC-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CUAIStudents/Qwen-Ar-GEC-4bit")
model = AutoModelForCausalLM.from_pretrained("CUAIStudents/Qwen-Ar-GEC-4bit")
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 CUAIStudents/Qwen-Ar-GEC-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CUAIStudents/Qwen-Ar-GEC-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CUAIStudents/Qwen-Ar-GEC-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CUAIStudents/Qwen-Ar-GEC-4bit

SGLang

How to use CUAIStudents/Qwen-Ar-GEC-4bit 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 "CUAIStudents/Qwen-Ar-GEC-4bit" \
    --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": "CUAIStudents/Qwen-Ar-GEC-4bit",
		"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 "CUAIStudents/Qwen-Ar-GEC-4bit" \
        --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": "CUAIStudents/Qwen-Ar-GEC-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CUAIStudents/Qwen-Ar-GEC-4bit with Docker Model Runner:
```
docker model run hf.co/CUAIStudents/Qwen-Ar-GEC-4bit
```

Qwen-Ar-GEC-4bit

This is a quantized version of Qwen-Ar-GEC.
It is smaller in size and optimized for GPU VRAM efficiency.

For usage examples, please refer to the original Qwen-Ar-GEC model card.
Both models are functionally identical, but when loading the 4-bit version you may need to include the following configuration:


from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
)

model_name = "Abdo-Alshoki/qwen-ar-gec-v2-4bit"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    quantization_config=bnb_config,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

⚠️ Note: The model is already quantized. Including the configuration ensures it is loaded correctly and runs as expected.

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16

F32

Collection including CUAIStudents/Qwen-Ar-GEC-4bit

Arabic GEC

Collection

This collection contains models the perform GEC or unambiguous • 5 items • Updated Sep 12, 2025