You can deploy this model and start earning money today!

kasumi-nakano/
qwen3-4b-structured-output-base

Name: qwen3-4b-structured-output-base
Availability: InStock

u-10bei/structured_data_with_cot_dataset_512_v4

daichira/structured-5k-mix-sft

Qwen/Qwen3-4B-Instruct-2507

adapter

apache-2.0

Views

No views yet

wen3-4b-structured-output-v4plus5k-v1

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
Datasets:
- u-10bei/structured_data_with_cot_dataset_512_v4 (4,608 samples, system prompt enhanced)
- daichira/structured-5k-mix-sft (filtered <1000 chars, ~2,500 samples)
Method: QLoRA (4-bit)
Max sequence length: 768
Epochs: 1
Learning rate: 1e-06
LoRA: 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 (MIT License)
daichira/structured-5k-mix-sft (MIT License)

Compliance: Users must comply with:

MIT License terms for both datasets (including copyright notice)
Base model's (Qwen3-4B-Instruct-2507) original terms of use

kasumi-nakano/qwen3-4b-structured-output-base

Training Objective

Training Configuration

Usage

Sources & Terms (IMPORTANT)

kasumi-nakano/
qwen3-4b-structured-output-base