Instructions to use beyoru/Qwen3-4B-I-1209 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beyoru/Qwen3-4B-I-1209 with Transformers:

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

pipe = pipeline("text-generation", model="beyoru/Qwen3-4B-I-1209")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use beyoru/Qwen3-4B-I-1209 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beyoru/Qwen3-4B-I-1209"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/Qwen3-4B-I-1209",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/beyoru/Qwen3-4B-I-1209

SGLang

How to use beyoru/Qwen3-4B-I-1209 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 "beyoru/Qwen3-4B-I-1209" \
    --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": "beyoru/Qwen3-4B-I-1209",
		"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 "beyoru/Qwen3-4B-I-1209" \
        --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": "beyoru/Qwen3-4B-I-1209",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use beyoru/Qwen3-4B-I-1209 with Docker Model Runner:
```
docker model run hf.co/beyoru/Qwen3-4B-I-1209
```

Qwen3-4B-I-1209

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

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

@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}}
}

Downloads last month: 180

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for beyoru/Qwen3-4B-I-1209

Unable to build the model tree, the base model loops to the model itself. Learn more.

Collection including beyoru/Qwen3-4B-I-1209

Agent-rc

Collection

Agent research, tool calling and ReAct • 3 items • Updated Mar 2