import torch
from modelscope import AutoModelForSequenceClassification, AutoTokenizer
model_name_or_path = "iic/gte_passage-ranking_multilingual-base"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForSequenceClassification.from_pretrained(model_name_or_path, trust_remote_code=True)
model.eval()
with torch.no_grad():
    pairs = [["中国的首都在哪儿", "北京"], ["what is the capital of China?", "北京"], ["how to implement quick sort in python?","Introduction of quick sort"]]
    inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=8192)
    scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
    print(scores)
# tensor([1.2315, 0.5923, 0.3041])

import requests
import torch
from PIL import Image
from io import BytesIO
from modelscope import snapshot_download
from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image
DEVICE = "cuda:0"
# Note that passing the image urls (instead of the actual pil images) to the processor is also possible
image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
image2 = load_image("https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg")
image3 = load_image("https://cdn.britannica.com/68/170868-050-8DDE8263/Golden-Gate-Bridge-San-Francisco.jpg")
model_dir = snapshot_download("AI-ModelScope/Idefics3-8B-Llama3")
processor = AutoProcessor.from_pretrained(model_dir)
model = AutoModelForVision2Seq.from_pretrained(
    model_dir, torch_dtype=torch.bfloat16
).to(DEVICE)
# Create inputs
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do we see in this image?"},
        ]
    },
    {
        "role": "assistant",
        "content": [
            {"type": "text", "text": "In this image, we can see the city of New York, and more specifically the Statue of Liberty."},
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "And how about this image?"},
        ]
    },       
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)