---
base_model: beyoru/Qwen3-4B-I-1209
tags:
- text-generation-inference
- transformers
- qwen3
- tools
- agent
- function calling
- tool calling
license: apache-2.0
language:
- en
---
# Qwen3-4B-I-1209
[![GitHub](https://img.shields.io/badge/GitHub-181717?style=flat-square&logo=github&logoColor=white)](https://github.com/Hert4)
[![HuggingFace](https://img.shields.io/badge/HuggingFace-FFD21E?style=flat-square&logo=huggingface&logoColor=black)](https://huggingface.co/beyoru)
[![Buy Me A Coffee](https://img.shields.io/badge/Buy_Me_A_Coffee-A78BFA?style=flat-square&logo=buy-me-a-coffee&logoColor=white)](https://buymeacoffee.com/ductransa0g)

Fine-tuned variant of Qwen3-4B-Instruct-2507, optimized for tool-use and function call generation via reinforcement learning with composite reward signals.

## Overview

| | |
|---|---|
| **Base Model** | Qwen/Qwen3-4B-Instruct-2507 |
| **Training Method** | GRPO (Group Relative Policy Optimization) |
| **Specialization** | Tool-use, function calling |
| **License** | Apache 2.0 |

## Training

### Reward Design

The model is trained with three complementary reward functions:

- **Rule-based reward** — Verifies correctness of function names and arguments. Partial credit is awarded for matching argument subsets.
- **Self-certainty reward** — Encourages confident, well-calibrated predictions.
- **Tool-call reward** — Validates structural correctness of generated tool calls.

### Configuration

| Parameter | Value |
|---|---|
| Optimizer | AdamW |
| Learning rate | 5e-6 |
| Scheduler | Cosine with min LR (`min_lr_rate=0.1`) |
| Generations per prompt | 4 |

## Evaluation

### ACEBench

| Model | Overall Accuracy |
|---|---|
| **Qwen3-4B-I-1209 (this model)** | **0.7233** |
| Qwen3-4B-Instruct-2507 (base) | 0.6350 |
| Salesforce/Llama-xLAM-2-8b-fc-r | 0.5792 |

> Additional benchmark results will be added as evaluation continues.

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("beyoru/Qwen3-4B-I-1209")
tokenizer = AutoTokenizer.from_pretrained("beyoru/Qwen3-4B-I-1209")
```

## Feedback & Contributions

Feedback on model quality, edge cases, and real-world performance is welcome. Open an issue or reach out via the links below.


## Citation

```bibtex
@misc{qwen3-4b-i-1209,
  title        = {Qwen3-4B-I-1209: Fine-tuned Qwen3-4B-Instruct with GRPO for Tool-Use and Function Calling},
  author       = {Beyoru},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/beyoru/Qwen3-4B-I-1209}}
}
```