Stepan222/oem-fake-classifier-qwen2vl

OEM/Fake Classifier (Qwen2.5-VL-7B-Instruct LoRA)

Fine-tuned LoRA adapter for classifying eBay listings as OEM (original) or Fake auto parts.

Model Details

• Base Model: Qwen/Qwen2.5-VL-7B-Instruct
• Adapter Type: LoRA (PEFT)
• Task: Binary classification (OEM vs Fake)
• LoRA Rank: 8
• LoRA Alpha: 16

Usage

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from peft import PeftModel

# Load base model
base_model = Qwen2VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-VL-7B-Instruct",
    torch_dtype="auto",
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "Stepan222/oem-fake-classifier-qwen2vl")
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")

Training

• Fine-tuned on Fireworks.ai
• Training loss: 0.044
• Epochs: 3