GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AISA-Framework
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
AISA-Framework
Model Tree
unsloth/functiongemma-270m-it
Input Modalities
Output Modalities
Supported Functionality
You can run a full inference example using the notebook below.
The notebook demonstrates:
| 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.
Supported domains:
| Domain |
|---|
| Travel |
| Utilities |
| Islamic services |
| Weather |
| Healthcare |
| Banking & finance |
| E-commerce |
| Government services |
The model is trained on AISA-AR-FunctionCall — a production-ready Arabic function-calling dataset built through a rigorous data-centric pipeline:
Dataset splits:
| Split | Samples |
|---|---|
| Train | 41,104 |
| Validation | 4,568 |
| Test | 5,079 |
Dataset includes:
Dataset: AISA-Framework/AISA-AR-FunctionCall
The model was trained using a data-centric fine-tuning pipeline designed to stabilize structured execution.
Key pipeline steps:
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 was performed on a held-out test set of 5,079 samples.
| 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 |
Key improvement: Parse failure reduced from 87% → <1%
| 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.
Remaining errors are primarily semantic, including:
Structured formatting errors are largely eliminated.
Prompt:
markdown
ما حالة الطقس في الرياض اليوم؟
Model output:
markdown
<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.
This model is designed for:
This model is not designed for:
| Model | Description |
|---|---|
| AISA-AR-FunctionCall-Think | Reasoning-augmented tool-calling model |
This model is part of the AISA initiative for building reliable agentic AI systems.
Model collection: AISA-Framework/aisa-arabic-functioncall-datasets-and-models
| 0.1274 |
| 0.9916 |
| Hallucination Rate | 0.0003 | 0.0226 |