Instructions to use GawinGowin/dpo-struct-output-sfted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GawinGowin/dpo-struct-output-sfted with Transformers:

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

pipe = pipeline("text-generation", model="GawinGowin/dpo-struct-output-sfted")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GawinGowin/dpo-struct-output-sfted")
model = AutoModelForCausalLM.from_pretrained("GawinGowin/dpo-struct-output-sfted", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GawinGowin/dpo-struct-output-sfted with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GawinGowin/dpo-struct-output-sfted"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GawinGowin/dpo-struct-output-sfted",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GawinGowin/dpo-struct-output-sfted

SGLang

How to use GawinGowin/dpo-struct-output-sfted 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 "GawinGowin/dpo-struct-output-sfted" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GawinGowin/dpo-struct-output-sfted",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "GawinGowin/dpo-struct-output-sfted" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GawinGowin/dpo-struct-output-sfted",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use GawinGowin/dpo-struct-output-sfted 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 GawinGowin/dpo-struct-output-sfted 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 GawinGowin/dpo-struct-output-sfted to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GawinGowin/dpo-struct-output-sfted to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="GawinGowin/dpo-struct-output-sfted",
    max_seq_length=2048,
)

Docker Model Runner
How to use GawinGowin/dpo-struct-output-sfted with Docker Model Runner:
```
docker model run hf.co/GawinGowin/dpo-struct-output-sfted
```

SFT Merged Model (DPO Base)

This model is a full-merged 16-bit version of Qwen/Qwen3-4B-Instruct-2507 with a Supervised Fine-Tuning (SFT) LoRA adapter merged into the base weights.

It serves as the base model for subsequent DPO training.

Training Pipeline

Qwen/Qwen3-4B-Instruct-2507  (base)
  |
  v
SFT via QLoRA (4-bit, Unsloth)
  - Objective: structured output accuracy (JSON / YAML / XML / TOML / CSV)
  - Adapter:   GawinGowin/lora-struct-output  (private)
  |
  v
Merge adapter into full weights -> this model
  |
  v
DPO -> GawinGowin/dpo-struct-output-sfted

SFT Configuration

Parameter	Value
Base model	Qwen/Qwen3-4B-Instruct-2507
Method	QLoRA (4-bit) + Unsloth
Training objective	Structured output (JSON / YAML / XML / TOML / CSV)
Dataset	u-10bei/structured_data_with_cot_dataset_512_v2
Max sequence length	512
Epochs	1
Learning rate	1e-6
LoRA r / alpha	64 / 128
CoT Masking	Enabled (loss applied after `Output:` marker only)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Use the DPO model for inference
model_id = "GawinGowin/dpo-struct-output-sfted"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.float16, device_map="auto",
)

Sources & License

Base model: Qwen/Qwen3-4B-Instruct-2507
SFT adapter: GawinGowin/lora-struct-output (private)
Training data: u-10bei/structured_data_with_cot_dataset_512_v2 — MIT License
License: Apache 2.0
Compliance: Users must comply with the MIT license of the training dataset and the original terms of use of the base model.

Downloads last month: 5

Safetensors

Model size

4B params

Tensor type

F16

Model tree for GawinGowin/dpo-struct-output-sfted

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1929)

this model

GawinGowin
/

dpo-struct-output-sfted