digo-prayudha/emotion_classification

from transformers import (PaliGemmaProcessor,PaliGemmaForConditionalGeneration,)
from transformers.image_utils import load_image
import torch
from transformers import BitsAndBytesConfig
from peft import get_peft_model
from huggingface_hub import login
from PIL import Image
login(api_key)

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

bnb_config = BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_type=torch.bfloat16
)

# Load base model
model_id = "google/paligemma-3b-pt-224"
model = PaliGemmaForConditionalGeneration.from_pretrained(model_id, quantization_config=bnb_config, device_map="auto")
processor = PaliGemmaProcessor.from_pretrained(model_id)

# Load adapter
adapter_path = "digo-prayudha/emotion_classification" 
model = PeftModel.from_pretrained(model, adapter_path)

image = Image.open("image.jpg").convert("RGB")

prompt = (
    "Classify the emotion expressed in this image."
)

inputs = processor(
    text=prompt,
    images=image,
    return_tensors="pt",
    padding="longest",
    tokenize_newline_separately=False
).to(model.device)

model.eval() 
with torch.no_grad():
    outputs = model.generate(**inputs)

decoded_output = processor.decode(outputs[0], skip_special_tokens=True)

print("Predicted Emotion:", decoded_output)