Instructions to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with Transformers:

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

pipe = pipeline("text-generation", model="AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m", dtype="auto")

llama-cpp-python

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m",
	filename="functiongemma_arabic_v5_Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

Use Docker

docker model run hf.co/AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

LM Studio
Jan

vLLM

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

SGLang

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m 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 "AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m" \
    --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": "AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m",
		"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 "AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m" \
        --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": "AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with Ollama:
```
ollama run hf.co/AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M
```

Unsloth Studio new

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m to start chatting

Pi new

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with Docker Model Runner:
```
docker model run hf.co/AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M
```

Lemonade

How to use AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m:Q4_K_M

Run and chat with the model

lemonade run user.AISA-AR-FunctionCall-FT-q4_k_m-Q4_K_M

List all available models

lemonade list

AISA-AR-FunctionCall-FT (Quantized Version 4 bit)

Reliable Arabic Structured Tool Calling via Data-Centric Fine-Tuning

AISA-AR-FunctionCall-FT is a fully fine-tuned Arabic function-calling model built on top of FunctionGemma (Gemma 3 270M) and optimized for structured tool invocation in Arabic agentic systems.

The model converts natural Arabic requests into structured executable API calls, enabling reliable integration between language models and external tools.

This model is part of the AISA (Agentic AI Systems Architecture) initiative.

Try the Model in Google Colab

You can run a full inference example using the notebook below.

The notebook demonstrates:

Loading the model
Defining tool schemas
Generating structured tool calls
Parsing function call outputs

Model Overview

Field	Value
Model name	AISA-AR-FunctionCall-FT
Base model	unsloth/functiongemma-270m-it
Architecture	Gemma 3 (270M parameters)
Fine-tuning type	Full-parameter supervised fine-tuning
Primary task	Arabic function calling / tool invocation

The model is designed to translate Arabic natural language requests into structured tool calls following the FunctionGemma tool-calling format.

Key Capabilities

Arabic natural language → structured API calls
Multi-dialect Arabic understanding
Tool selection and argument extraction
Structured execution environments

Supported domains:

Domain
Travel
Utilities
Islamic services
Weather
Healthcare
Banking & finance
E-commerce
Government services

Dataset

The model is trained on AISA-AR-FunctionCall — a production-ready Arabic function-calling dataset built through a rigorous data-centric pipeline:

Dataset auditing
Schema normalization
Enum correction
Tool pruning
Prompt restructuring
Tool sampling

Dataset splits:

Split	Samples
Train	41,104
Validation	4,568
Test	5,079

Dataset includes:

5 Arabic dialects
8 real-world domains
27 tool schemas
Structured tool-call annotations

Dataset: AISA-Framework/AISA-AR-FunctionCall

Training Methodology

The model was trained using a data-centric fine-tuning pipeline designed to stabilize structured execution.

Key pipeline steps:

Structural dataset auditing
Enum constraint repair
Tool schema normalization
Tool pruning (36 → 27 tools)
Tool sampling to prevent prompt truncation
FunctionGemma-compatible chat serialization
Completion-only supervised fine-tuning

Training configuration:

Parameter	Value
Model size	270M
Training type	Full fine-tuning
Epochs	2
Effective batch size	32
Learning rate	2e-5
Optimizer	8-bit AdamW
Scheduler	Cosine
Precision	BF16
Gradient checkpointing	Enabled

Evaluation Results

Evaluation was performed on a held-out test set of 5,079 samples.

Clean Positive Evaluation (n = 2,873)

Metric	Baseline	AISA-AR-FunctionCall-FT
Function Name Accuracy	0.0804	0.6547
Full Tool-Call Match	0.0056	0.3362
Argument Key F1	0.0600	0.5728
Argument Exact Match	0.0422	0.6377
Parse Failure Rate	0.8726	0.0084
Format Validity	0.1274	0.9916
Hallucination Rate	0.0003	0.0226

Key improvement: Parse failure reduced from 87% → <1%

Dialect Performance

Dialect	Function Accuracy
MSA	0.761
Gulf	0.697
Egyptian	0.683
Levantine	0.694
Maghrebi	0.616

Fine-tuning significantly reduces dialect disparity compared to the baseline model.

Known Limitations

Remaining errors are primarily semantic, including:

Tool selection ambiguity
Argument mismatches
Domain overlap (e.g., weather vs. air quality)

Structured formatting errors are largely eliminated.

Example Usage

Prompt:

ما حالة الطقس في الرياض اليوم؟

Model output:

<start_function_call>
call:get_weather{
  city:<escape>الرياض<escape>,
  days:1
}
<end_function_call>

The structured call can then be executed by the application runtime.

Intended Use

This model is designed for:

Arabic AI assistants
Tool-based agents
Structured API orchestration
Arabic enterprise automation
Research on multilingual tool calling

Out-of-Scope Uses

This model is not designed for:

General chatbots or open-ended conversation
Sensitive decision-making systems
Safety-critical deployments without additional validation

Related Models

Model	Description
AISA-AR-FunctionCall-Think	Reasoning-augmented tool-calling model

AISA Framework

This model is part of the AISA initiative for building reliable agentic AI systems.

Model collection: AISA-Framework/aisa-arabic-functioncall-datasets-and-models

License

Apache 2.0

Downloads last month: 12

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

4-bit

Model tree for AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m

Base model

google/functiongemma-270m-it

Finetuned

unsloth/functiongemma-270m-it

Quantized

(8)

this model

Dataset used to train AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m

Collection including AISA-Framework/AISA-AR-FunctionCall-FT-q4_k_m

AISA Arabic FunctionCall: Datasets & Models

Collection

A collection of Arabic datasets and models for structured tool calling and agentic AI systems. • 6 items • Updated Mar 19 • 6