o-ckun/

qwen3-4b-data2_123-lora-sft1

qwen3-4b-structured-output-lora-by-data2_combine_1

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.

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 data: daichira/structured-3k-mix-sft ; daichira/structured-5k-mix-sft ; daichira/structured-hard-sft-4k

Dataset License: CC-BY-4.0 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.