llm/image_description.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from PIL import Image

model = AutoModelForCausalLM.from_pretrained(
    "openbmb/MiniCPM-Llama3-V-2_5",
    trust_remote_code=True
)

print(model)

tokenizer = AutoTokenizer.from_pretrained(
    "openbmb/MiniCPM-Llama3-V-2_5",
    trust_remote_code=True
)

image = Image.open("fridge.JPG")
prompt = "What is the main object shown in the image? Describe in less than 5 words, as a name for it."

# First round chat 
# question = "Tell me the model of this aircraft."
msgs = [{'role': 'user', 'content': [image, prompt]}]

answer = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer
)
print(answer)


# chat = model.chat(
#     image=image, 
#     question=prompt, 
#     tokenizer=tokenizer,
#     generate_args={"temperature": 0.8}
# )

# print(chat)