follmon10/qwen3-4b-structured-output-lora_sft_v2_2ep5e-5_uns_1b16s_l4_4096cot0

qwen3-4b-structured-output-lorasftv22ep5e-5uns1b16sl4_4096cot0

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).

Training Configuration

• —Base model: unsloth/Qwen3-4B-Instruct-2507
• —Method: QLoRA (4-bit)
• —Max sequence length: 4096
• —Epochs: 2
• —Learning rate: 5e-05
• —LoRA: r=64, alpha=128

Sources & Terms

Training data: u-10bei/structureddatawithcotdataset, daichira/structured-hard-sft-4k