This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507, first trained with SFT (Supervised Fine-Tuning) for structured output accuracy, then further aligned 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 was trained in two stages:

SFT: Fine-tuned on structured output data (JSON/YAML/XML/TOML/CSV) with Chain-of-Thought reasoning.
DPO: Further aligned using preference pairs to improve output quality and format compliance.

Training Configuration

Base model: Qwen/Qwen3-4B-Instruct-2507
Method: SFT (QLoRA) → DPO
SFT dataset: u-10bei/structured_data_with_cot_dataset_512_v2
DPO dataset: u-10bei/dpo-dataset-qwen-cot
Epochs: 1
Learning rate: 1e-07
Beta: 0.1
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.

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Hkumomo/qwen3-4b-sft-dpo-structured-output-merged"

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

# Test inference
prompt = "Your question here"
inputs = tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

Sources & License (IMPORTANT)

SFT Training Data: [u-10bei/structured_data_with_cot_dataset_512_v2]
DPO 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.