icu-mama-cooking / README.md
kxm1k4m1's picture
Create README.md
195bfc0 verified
metadata
library_name: transformers
license: mit
language:
  - th
pipeline_tag: image-to-text
base_model: Salesforce/blip2-opt-2.7b-coco

THAI-BLIP-2

fine-tuned for image captioning task from blip2-opt-2.7b-coco with MSCOCO2017 thai caption.

How to use:

from transformers import Blip2ForConditionalGeneration, Blip2Processor
from PIL import Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

processor = Blip2Processor.from_pretrained("kxm1k4m1/icu-mama-cooking")
model = Blip2ForConditionalGeneration.from_pretrained("kxm1k4m1/icu-mama-cooking", device_map=device, torch_dtype=torch.bfloat16)

img = Image.open("Your image...")
inputs = processor(images=img, return_tensors="pt").to(device, torch.bfloat16)

# Adjust your `max_length`
generated_ids = model.generate(**inputs, max_length=20)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_text)