import requests
import torch
from PIL import Image
from io import BytesIO

from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image

DEVICE = "cuda:0"

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")

processor = AutoProcessor.from_pretrained("GeorgeBredis/ruIdefics2-ruLLaVA-merged")
model = AutoModelForVision2Seq.from_pretrained(
    "GeorgeBredis/ruIdefics2-ruLLaVA-merged",
).to(DEVICE)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Что изображено на данной картинке?"},
        ]
    }
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}


generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)

print(generated_texts)

Вполне возможно что это не влезет в вашу GPU (если будете загружать на gpu), так что ниже вариант с bnb для запуска в colab'e.

Запуск в int4/int8 c bnb.

Требует установки peft

python

import requests
import torch
from PIL import Image
from io import BytesIO

from peft import LoraConfig
from transformers import AutoProcessor, BitsAndBytesConfig, Idefics2ForConditionalGeneration
from transformers.image_utils import load_image

DEVICE = "cuda:0"

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")

processor = AutoProcessor.from_pretrained(
    "GeorgeBredis/ruIdefics2-ruLLaVA-merged",
    do_image_splitting=False
)

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_use_double_quant=True,
    bnb_4bit_compute_dtype=torch.float16
)
model = Idefics2ForConditionalGeneration.from_pretrained(
     "GeorgeBredis/ruIdefics2-ruLLaVA-merged",
     torch_dtype=torch.float16,    
     quantization_config=quantization_config,
)
# не нужно переносить на карту, так как в int4/8 заводятся сразу на них

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Что изображено на данной картинке?"},
        ]
    }
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}


generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)

print(generated_texts)