You can deploy this model and start earning money today!

sergiudanstan/
smolvlm2-2.2b-foodextract-lora

Name: smolvlm2-2.2b-foodextract-lora
Availability: InStock

mrdbourke/FoodExtract-1k-Vision

HuggingFaceTB/SmolVLM2-2.2B-Instruct

adapter

Views

No views yet

SmolVLM2-500M FoodExtract LoRA

LoRA adapter for HuggingFaceTB/SmolVLM2-2.2B-Instruct, fine-tuned on mrdbourke/FoodExtract-1k-Vision.

Given a food/drink image it returns structured JSON:

json

{"is_food": 1, "image_title": "salad",
 "food_items": ["tomato", "lettuce"], "drink_items": []}

Usage

python

from transformers import AutoProcessor, AutoModelForImageTextToText
from peft import PeftModel

base = "HuggingFaceTB/SmolVLM2-2.2B-Instruct"
processor = AutoProcessor.from_pretrained(base)
model = AutoModelForImageTextToText.from_pretrained(base)
model = PeftModel.from_pretrained(model, "sergiudanstan/smolvlm2-2.2b-foodextract-lora").merge_and_unload()