qwen3-4b-runb-clean-lora
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: 2
- Learning rate: 5e-6
- LoRA: r=16, alpha=32
Training data details
Run B uses a cleaned local JSONL built from official datasets:
/content/structeval_runB_clean.jsonl
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "yuk1chan/qwen3-4b-runb-clean-lora"
tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(
base,
torch_dtype=torch.float16,
device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter)
