llm2025-qwen3-4b-structured-output-lora-02

llm2025-qwen3-4b-structured-output-lora-02

This repository provides a LoRA adapter fine-tuned from unsloth/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth).

This repository contains LoRA adapter weights only. The base model must be loaded separately.

Training Objective

This adapter is trained to improve structured output accuracy (JSON / YAML / XML / TOML / CSV).

Loss is applied only to the final assistant output, while intermediate reasoning (Chain-of-Thought) is masked.

Training Configuration

• Base model: unsloth/Qwen3-4B-Instruct-2507
• Method: QLoRA (4-bit)
• Max sequence length: 512
• Epochs: 1
• Learning rate: 2e-05
• LoRA: r=32, alpha=64

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base = "unsloth/Qwen3-4B-Instruct-2507"
adapter = "your_id/your-repo"

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

Sources & License (IMPORTANT)

• Training Data: u-10bei/structured_data_with_cot_dataset_512_v5
• Dataset License: MIT License
• Compliance: This dataset is used and distributed under the terms of the MIT License. Users must comply with the MIT license (including the copyright notice) and the base model's original terms of use.