metadata
base_model: Qwen/Qwen3-4B-Instruct-2507
datasets:
- u-10bei/structured_data_with_cot_dataset
language:
- en
license: apache-2.0
library_name: peft
pipeline_tag: text-generation
tags:
- qlora
- lora
- structured-output
＜clean version 3＞
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)
- Max sequence length: 2048
- Epochs: 3
- Learning rate: 2e-06
- LoRA: r=64, alpha=128
Sources & Terms (IMPORTANT)
Training data: u-10bei/structured_data_with_cot_dataset
Dataset License: MIT License. Compliance: Users must comply with the MIT license and the base model's original terms of use.