You can deploy this model and start earning money today!

ryo-llm/
qwen3-4b-structured-output-lora-202602081359

Name: qwen3-4b-structured-output-lora-202602081359
Availability: InStock

u-10bei/structured_data_with_cot_dataset_512_v5

Qwen/Qwen3-4B-Instruct-2507

adapter

apache-2.0

Views

No views yet

qwen3-4b-structured-output-lora-202602081359

This repository provides a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth) to improve structured output accuracy (JSON / YAML / XML / TOML / CSV).

This repository contains LoRA adapter weights only. Load the base model separately, then apply this adapter.

Training Objective

Improve strict, machine-readable structured outputs (no extra prose).

Data Normalization

To reduce preface/explanation text learned from the synthetic dataset, the training samples were normalized:

Extracted only the substring after Output: in the final assistant message.
Removed Markdown code fences (json/yaml/xml/toml/```csv).
Dropped trailing "Notes:" sections if present.

Training Configuration

Base model: Qwen/Qwen3-4B-Instruct-2507
Method: QLoRA (4-bit), Unsloth
Max sequence length: 512
Epochs: 2
Learning rate: 1e-05
LoRA: r=16, alpha=32

Usage

python

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

base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "ryo-llm/qwen3-4b-structured-output-lora-202602081359"

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

## Sources & Terms (IMPORTANT)

Training data: u-10bei/structured_data_with_cot_dataset_512_v5

Dataset License: MIT License (see the dataset card).
Compliance: Users must comply with the dataset license terms and the base model's original terms of use.