lora-structeval-qwen3-4b

Yurori/lora-structeval-qwen3-4b

This repository provides a LoRA adapter fine-tuned from Qwen/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: Qwen/Qwen3-4B-Instruct-2507
• Method: QLoRA (4-bit, unsloth)
• Max sequence length: 1024
• Epochs: 1
• Learning rate: 1e-6
• LoRA parameters: r=64, alpha=128

Usage

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

base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "Yurori/lora-structeval-qwen3-4b"

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_v2
• Dataset License: Creative Commons Attribution (CC-BY-4.0). This dataset is used and can be redistributed under the terms of the CC-BY-4.0 license.
• Compliance: Users must comply with both the dataset's attribution requirements and the base model's original terms of use.