Instructions to use curio184/qwen3-4b-struct-exp48 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use curio184/qwen3-4b-struct-exp48 with Transformers:

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

pipe = pipeline("text-generation", model="curio184/qwen3-4b-struct-exp48")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("curio184/qwen3-4b-struct-exp48")
model = AutoModelForCausalLM.from_pretrained("curio184/qwen3-4b-struct-exp48")
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

vLLM

How to use curio184/qwen3-4b-struct-exp48 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "curio184/qwen3-4b-struct-exp48"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "curio184/qwen3-4b-struct-exp48",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/curio184/qwen3-4b-struct-exp48

SGLang

How to use curio184/qwen3-4b-struct-exp48 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 "curio184/qwen3-4b-struct-exp48" \
    --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": "curio184/qwen3-4b-struct-exp48",
		"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 "curio184/qwen3-4b-struct-exp48" \
        --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": "curio184/qwen3-4b-struct-exp48",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use curio184/qwen3-4b-struct-exp48 with Docker Model Runner:
```
docker model run hf.co/curio184/qwen3-4b-struct-exp48
```

qwen3-4b-struct-exp48

This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth).

This repository contains the full merged 16-bit weights. No adapter loading is required.

Training Objective

This model is trained to improve structured output accuracy (JSON / YAML / XML / TOML / CSV).

Training Configuration

Base model: Qwen/Qwen3-4B-Instruct-2507
Dataset: u-10bei/structured_data_with_cot_dataset_512_v2
Method: QLoRA (4-bit)
Max sequence length: 512
Epochs: 3
Learning rate: 1e-06
LoRA: r=64, alpha=128

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "curio184/qwen3-4b-struct-exp48"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
)

Sources & Terms (IMPORTANT)

Training data: u-10bei/structured_data_with_cot_dataset_512_v2

Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License. Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

Downloads last month: 1

Safetensors

Model size

4B params

Tensor type

F32

F16

Model tree for curio184/qwen3-4b-struct-exp48

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5477)

this model

curio184
/

qwen3-4b-struct-exp48