Instructions to use QCRI/Fanar-1-9B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QCRI/Fanar-1-9B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="QCRI/Fanar-1-9B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QCRI/Fanar-1-9B-Instruct")
model = AutoModelForCausalLM.from_pretrained("QCRI/Fanar-1-9B-Instruct")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use QCRI/Fanar-1-9B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QCRI/Fanar-1-9B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QCRI/Fanar-1-9B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QCRI/Fanar-1-9B-Instruct

SGLang

How to use QCRI/Fanar-1-9B-Instruct 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 "QCRI/Fanar-1-9B-Instruct" \
    --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": "QCRI/Fanar-1-9B-Instruct",
		"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 "QCRI/Fanar-1-9B-Instruct" \
        --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": "QCRI/Fanar-1-9B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QCRI/Fanar-1-9B-Instruct with Docker Model Runner:
```
docker model run hf.co/QCRI/Fanar-1-9B-Instruct
```

Fanar-1-9B-Instruct

Commit History

Update max_position_embeddings in model config to 4096

d30938d
verified

shamz15531 commited on Jul 15, 2025

Update model_max_length in tokenizer config to 4096

090429e
verified

shamz15531 commited on Jul 15, 2025

Update README.md

8a7f56e
verified

shamz15531 commited on Jun 5, 2025

Update README.md

4d50b8f
verified

shamz15531 commited on Jun 5, 2025

Update README.md

fa6a7ea
verified

shamz15531 commited on Jun 4, 2025

Upload fanar_logo.jpg

7e3d2fa
verified

shamz15531 commited on Jun 4, 2025

Rename Fanar Logo.jpg to fanar_logo.jpg

48698b8
verified

shamz15531 commited on Jun 4, 2025

Upload Fanar Logo.jpg

3c175dd
verified

shamz15531 commited on Jun 4, 2025

Update README.md

6e5d11e
verified

shamz15531 commited on Jun 4, 2025

Update README.md

e7018d4
verified

shamz15531 commited on Jun 4, 2025

Update README.md

595dc6b
verified

shamz15531 commited on Jun 4, 2025

Update README.md

a3ddb25
verified

shamz15531 commited on Jun 4, 2025

Update README.md

fc4d957
verified

shamz15531 commited on Jun 3, 2025

Update README.md

edd043a
verified

shamz15531 commited on Jun 3, 2025

Update README.md

137f864
verified

shamz15531 commited on Jun 2, 2025

Update README.md

617d56a
verified

shamz15531 commited on Jun 2, 2025

Update README.md

8a5e0bc
verified

shamz15531 commited on Jun 2, 2025

Add tokenizer.model via Git LFS

f9205a9

Mohammed Shahmeer (QCRI) commited on Jun 1, 2025

Re-add tokenizer.model with Git LFS tracking

a7e8f0d

Mohammed Shahmeer (QCRI) commited on Jun 1, 2025