Modelpublic

FumihiroToko/qwen3-4b-structeval-day10-sft

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

0likes12downloads

Model Card

Qwen3-4B-StructEval-Day10-SFT

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: 1024
—Epochs: 1
—Learning rate: 2e-04
—LoRA: r=64, alpha=128

Usage

python

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

base = "Qwen/Qwen3-4B-Instruct-2507"
# Note: Replace 'your_id' with your actual Hugging Face username
adapter = "your_id/qwen3-4b-structeval-day10-sft" 

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

Training data: u-10bei/structured_data_with_cot_dataset_512_v2

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.