lora_structeval_t_qwen3_4b_iku1

lora_structeval_t_qwen3_4b_iku1

This repository provides a LoRA adapter fine-tuned from unsloth/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: unsloth/Qwen3-4B-Instruct-2507

• Method: QLoRA (4-bit)

• Max sequence length: 1024

• Epochs: 1

• Learning rate: 1e-05

• LoRA: r=64, alpha=128

• Seed: 3407

• Validation split: 0.05

• Per-device train batch size: 1

• Per-device eval batch size: 2

• Gradient accumulation: 16

• Effective batch size: 16

• Weight decay: 0.02

• LoRA dropout: 0.05

• Target modules: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj

Usage

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

base = "unsloth/Qwen3-4B-Instruct-2507"
adapter = "Ikushima/lora_structeval_t_qwen3_4b_iku1"

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

Output Loss Masking

• Mask CoT: 1
• Output markers: Output:,OUTPUT:,Final:,Answer:,Result:,Response:
• Output learn mode: after_marker

Sources & Terms (IMPORTANT)

Training data: u-10bei/structured_data_with_cot_dataset_512_v5

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.