Instructions to use TuwaiqAcademy/AISA-AR-FunctionCall-Think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TuwaiqAcademy/AISA-AR-FunctionCall-Think with Transformers:

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

pipe = pipeline("text-generation", model="TuwaiqAcademy/AISA-AR-FunctionCall-Think")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TuwaiqAcademy/AISA-AR-FunctionCall-Think")
model = AutoModelForCausalLM.from_pretrained("TuwaiqAcademy/AISA-AR-FunctionCall-Think")
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 TuwaiqAcademy/AISA-AR-FunctionCall-Think with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TuwaiqAcademy/AISA-AR-FunctionCall-Think

SGLang

How to use TuwaiqAcademy/AISA-AR-FunctionCall-Think 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 "TuwaiqAcademy/AISA-AR-FunctionCall-Think" \
    --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": "TuwaiqAcademy/AISA-AR-FunctionCall-Think",
		"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 "TuwaiqAcademy/AISA-AR-FunctionCall-Think" \
        --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": "TuwaiqAcademy/AISA-AR-FunctionCall-Think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TuwaiqAcademy/AISA-AR-FunctionCall-Think with Docker Model Runner:
```
docker model run hf.co/TuwaiqAcademy/AISA-AR-FunctionCall-Think
```

Omartificial-Intelligence-Space commited on 4 days ago

Commit

a400e15

verified ·

1 Parent(s): 63ef237

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -53,7 +53,7 @@ model-index:
 A compact (**270M-parameter**) Arabic function-calling model that, given an Arabic user query (in any of 5 dialects) and a set of candidate tools, **writes a short Arabic `<think>` reasoning trace and then emits a structured tool call**. Fine-tuned (LoRA) from **[google/gemma-3-270m](https://huggingface.co/google/gemma-3-270m)** on the AISA-ArabicFC reasoning data.
-For the non-reasoning Track A baseline, see the sibling model **[AISA-AR-FunctionCall-FT](https://huggingface.co/TuwaiqAcademy/AISA-AR-FunctionCall-FT)**.
 ---

 A compact (**270M-parameter**) Arabic function-calling model that, given an Arabic user query (in any of 5 dialects) and a set of candidate tools, **writes a short Arabic `<think>` reasoning trace and then emits a structured tool call**. Fine-tuned (LoRA) from **[google/gemma-3-270m](https://huggingface.co/google/gemma-3-270m)** on the AISA-ArabicFC reasoning data.
+For the non-reasoning Track A baseline, see the sibling model **[AISA-AR-FunctionCall-FT](https://huggingface.co/AISA-Framework/AISA-AR-FunctionCall-FT)**.
 ---