---
base_model: Qwen/Qwen3-4B-Instruct-2507
datasets:
- u-10bei/structured_data_with_cot_dataset_512_v4
language:
- en
license: apache-2.0
library_name: peft
pipeline_tag: text-generation
tags:
- qlora
- lora
- structured-output
---

qwen3-4b-structured-output-lora-v4-2epoch

This repository provides a **LoRA adapter** fine-tuned from  
**Qwen/Qwen3-4B-Instruct-2507** using **QLoRA (4-bit quantization) with Hugging Face Transformers and PEFT**.

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 during training**.

## Training Configuration

- Base model: Qwen/Qwen3-4B-Instruct-2507
- Training framework: Hugging Face Transformers + PEFT
- Method: QLoRA (4-bit quantization, NF4)
- Max sequence length: 2048
- Epochs: 2
- Learning rate: 2e-6
- LoRA configuration: r=64, alpha=128

## Usage

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

base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "your_id/your-repo"

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_v4

Dataset License: MIT 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.