by0101/qwen3-4b-star-qlora-r16-v1

Qwen3-4B STAR QLoRA

This repository contains a LoRA adapter fine-tuned from Qwen/Qwen3-4B for STAR (Situation, Task, Action, Result) interview answer analysis.

Model Details

• —Base model: Qwen/Qwen3-4B
• —Model type: LoRA / QLoRA adapter
• —Library: PEFT
• —Task: STAR interview answer analysis
• —Pipeline: Text generation

Usage

This repository contains only the LoRA adapter. Load it together with the base model.

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_name = "Qwen/Qwen3-4B"
adapter_name = "by0101/qwen3-4b-star-qlora-r16-v1"

tokenizer = AutoTokenizer.from_pretrained(base_model_name)

base_model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    device_map="auto",
)

model = PeftModel.from_pretrained(
    base_model,
    adapter_name,
)

Files

• —adapter_model.safetensors: LoRA adapter weights
• —adapter_config.json: LoRA configuration
• —Tokenizer configuration files

Framework Versions

• —PEFT: 0.19.1