Instructions to use kabuizuchi-trading/gdpo-qwen-structured-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kabuizuchi-trading/gdpo-qwen-structured-merged with Transformers:

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

pipe = pipeline("text-generation", model="kabuizuchi-trading/gdpo-qwen-structured-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kabuizuchi-trading/gdpo-qwen-structured-merged")
model = AutoModelForCausalLM.from_pretrained("kabuizuchi-trading/gdpo-qwen-structured-merged")
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 kabuizuchi-trading/gdpo-qwen-structured-merged with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kabuizuchi-trading/gdpo-qwen-structured-merged

SGLang

How to use kabuizuchi-trading/gdpo-qwen-structured-merged 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 "kabuizuchi-trading/gdpo-qwen-structured-merged" \
    --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": "kabuizuchi-trading/gdpo-qwen-structured-merged",
		"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 "kabuizuchi-trading/gdpo-qwen-structured-merged" \
        --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": "kabuizuchi-trading/gdpo-qwen-structured-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use kabuizuchi-trading/gdpo-qwen-structured-merged 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 kabuizuchi-trading/gdpo-qwen-structured-merged 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 kabuizuchi-trading/gdpo-qwen-structured-merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kabuizuchi-trading/gdpo-qwen-structured-merged to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="kabuizuchi-trading/gdpo-qwen-structured-merged",
    max_seq_length=2048,
)

Docker Model Runner
How to use kabuizuchi-trading/gdpo-qwen-structured-merged with Docker Model Runner:
```
docker model run hf.co/kabuizuchi-trading/gdpo-qwen-structured-merged
```

SFT + GDPO trained Qwen3-4B for Structured Output

This model was trained in two phases:

SFT (Supervised Fine-Tuning) for structured output basics
GDPO (Group reward-Decoupled Normalization Policy Optimization) for multi-reward RL refinement

This repository contains the full-merged 16-bit weights.

GDPO Training (Phase 2)

GDPO (arxiv 2601.05242, NVIDIA Research) decouples reward normalization across individual rewards, preserving their relative differences.

Reward Functions

#	Reward	Weight	Description
1	Format Compliance	1.0	Approach/Output structure
2	Structured Output Validity	3.0	JSON/XML/YAML/TOML/CSV parsing
3	Output Length	0.3	Appropriate length
4	No Repetition	0.5	Prevents degeneration

Configuration

Method: GDPO (reward_aggregation=normalize_then_sum)
scale_rewards: none
LoRA: r=16, alpha=32
Learning rate: 5e-07
Beta: 0.01
Num generations: 8
Max steps: 300
Max completion length: 384
Dataset size: 2000 prompts (subsampled)
GPU: NVIDIA A100 80GB (bf16)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "kabuizuchi-trading/gdpo-qwen-structured-merged"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto",
)

Sources & License

GDPO Paper: https://arxiv.org/abs/2601.05242
License: Apache-2.0

Downloads last month: 12

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for kabuizuchi-trading/gdpo-qwen-structured-merged

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1704)

this model

Dataset used to train kabuizuchi-trading/gdpo-qwen-structured-merged

Paper for kabuizuchi-trading/gdpo-qwen-structured-merged

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published Jan 8 • 232