Instructions to use sonodd/qwen3-4b-structeval-dpo-v7-beta005 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sonodd/qwen3-4b-structeval-dpo-v7-beta005 with Transformers:

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

pipe = pipeline("text-generation", model="sonodd/qwen3-4b-structeval-dpo-v7-beta005")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sonodd/qwen3-4b-structeval-dpo-v7-beta005")
model = AutoModelForCausalLM.from_pretrained("sonodd/qwen3-4b-structeval-dpo-v7-beta005")
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 sonodd/qwen3-4b-structeval-dpo-v7-beta005 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sonodd/qwen3-4b-structeval-dpo-v7-beta005"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sonodd/qwen3-4b-structeval-dpo-v7-beta005",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sonodd/qwen3-4b-structeval-dpo-v7-beta005

SGLang

How to use sonodd/qwen3-4b-structeval-dpo-v7-beta005 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 "sonodd/qwen3-4b-structeval-dpo-v7-beta005" \
    --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": "sonodd/qwen3-4b-structeval-dpo-v7-beta005",
		"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 "sonodd/qwen3-4b-structeval-dpo-v7-beta005" \
        --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": "sonodd/qwen3-4b-structeval-dpo-v7-beta005",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use sonodd/qwen3-4b-structeval-dpo-v7-beta005 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 sonodd/qwen3-4b-structeval-dpo-v7-beta005 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 sonodd/qwen3-4b-structeval-dpo-v7-beta005 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sonodd/qwen3-4b-structeval-dpo-v7-beta005 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="sonodd/qwen3-4b-structeval-dpo-v7-beta005",
    max_seq_length=2048,
)

Docker Model Runner
How to use sonodd/qwen3-4b-structeval-dpo-v7-beta005 with Docker Model Runner:
```
docker model run hf.co/sonodd/qwen3-4b-structeval-dpo-v7-beta005
```

Qwen3-4B StructEval qwen3-4b-structeval-dpo-v7-beta005

This model is a fine-tuned version of sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged using Direct Preference Optimization (DPO) via the Unsloth library.

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

Training Objective

This model has been optimized using DPO to align its responses with preferred outputs, focusing on improving structured output quality (JSON, YAML, XML, TOML, CSV).

Training Configuration

Base model: sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged
SFT Adapter: None (merged SFT used as base)
Method: DPO (Direct Preference Optimization)
Epochs: 1
Learning rate: 1e-07
Beta: 0.05
Max sequence length: 1024
LoRA Config: r=8, alpha=16 (merged into base)

Usage

Since this is a merged model, you can use it directly with transformers.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "sonodd/qwen3-4b-structeval-dpo-v7-beta005"

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

Inference with Standard Code 2

For inference using the competition's standard code 2, set:

MODEL_SOURCE = "merged"
MERGED_MODEL_ID_OR_PATH = "sonodd/qwen3-4b-structeval-dpo-v7-beta005"

Sources & License (IMPORTANT)

Training Data: u-10bei/dpo-dataset-qwen-cot
License: MIT License (as per dataset terms)
Compliance: Users must follow the original base model's license terms.

Downloads last month: 4

Safetensors

Model size

4B params

Tensor type

F16

Model tree for sonodd/qwen3-4b-structeval-dpo-v7-beta005

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged