Instructions to use NAMAA-Space/Arabic-Sahm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NAMAA-Space/Arabic-Sahm with Transformers:

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

pipe = pipeline("text-generation", model="NAMAA-Space/Arabic-Sahm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NAMAA-Space/Arabic-Sahm", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NAMAA-Space/Arabic-Sahm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NAMAA-Space/Arabic-Sahm

SGLang

How to use NAMAA-Space/Arabic-Sahm 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 "NAMAA-Space/Arabic-Sahm" \
    --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": "NAMAA-Space/Arabic-Sahm",
		"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 "NAMAA-Space/Arabic-Sahm" \
        --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": "NAMAA-Space/Arabic-Sahm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NAMAA-Space/Arabic-Sahm with Docker Model Runner:
```
docker model run hf.co/NAMAA-Space/Arabic-Sahm
```

Request Access to This Research Model

This model is released for research purposes. Please provide your official information so we can keep track of model usage.

By requesting access, you confirm that the information provided is accurate and that you will use the model responsibly for research or development.

Gated model

You can list files but not access them

Preview of files found in this repository

NAMAA-Space
/

Arabic-Sahm

Request Access to This Research Model

Gated model

You can list files but not access them

Detected Pickle imports (3)

Detected Pickle imports (7)

Pickle imports

Detected Pickle imports (10)

Request Access to This Research Model

Gated model You can list files but not access them

Detected Pickle imports (3)

Detected Pickle imports (7)

Pickle imports

Detected Pickle imports (10)

Gated model

You can list files but not access them