You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Gretchen Image Model

LoRA adapter for Qwen/Qwen2.5-Omni-3B, fine-tuned for real vs fake image classification.

Base model

Qwen/Qwen2.5-Omni-3B

Training

Run: qwen-3b-1m-resume-2/v4-20260508-063751
Checkpoint: checkpoint-20000
LoRA rank: 64, alpha: 16, dropout: 0.05

Usage (ms-swift)

swift infer \
  --infer_backend pt \
  --val_dataset <your_dataset.jsonl> \
  --adapters 01Yassine/gretchen_image_model \
  --temperature 0

Usage (PEFT)

from peft import PeftModel
from transformers import Qwen2_5OmniForConditionalGeneration, AutoProcessor

base = Qwen2_5OmniForConditionalGeneration.from_pretrained("Qwen/Qwen2.5-Omni-3B")
model = PeftModel.from_pretrained(base, "01Yassine/gretchen_image_model")
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-Omni-3B")

Downloads last month: 10

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for 01Yassine/gretchen_image_model

Base model

Qwen/Qwen2.5-Omni-3B

Adapter

(33)

this model