qwen3-4b-struct-exp14

This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507 using SFT + DPO (2-stage fine-tuning).

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

Stage 1: SFT (Supervised Fine-Tuning)

• 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

Stage 2: DPO (Direct Preference Optimization)

• Dataset: u-10bei/dpo-dataset-qwen-cot
• Beta: 0.3
• Learning rate: 5e-07
• Epochs: 2
• LoRA: r=32, alpha=64

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "curio184/qwen3-4b-struct-exp14"

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.