import requests
from PIL import Image

import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration

model_id = "vonjack/Nous-Hermes-2-Pro-Xtuner-LLaVA-v1_1-Llama-3-8B"

prompt = ("<|im_start|>user\n<image>\nWhat are these?<|im_end|>"
          "<|im_start|>assistant\n")
image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"

model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True, 
).to(0)

processor = AutoProcessor.from_pretrained(model_id)


raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16)

output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
print(processor.decode(output[0][2:], skip_special_tokens=True))

Example: