File size: 716 Bytes
27b85fa 72c1f4c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 |
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
import requests
from io import BytesIO
url = "https://d2h50zujfkj84t.cloudfront.net/product_images/Screenshot_2024-09-03_135657.png"
response = requests.get(url)
image = Image.open(BytesIO(response.content))
model = AutoModelForCausalLM.from_pretrained(
"qresearch/llama-3.1-8B-vision-378",
trust_remote_code=True,
torch_dtype=torch.float16,
).to("cpu")
tokenizer = AutoTokenizer.from_pretrained("qresearch/llama-3.1-8B-vision-378", use_fast=True,)
print(
model.answer_question(
image, "Briefly describe the image", tokenizer, max_new_tokens=128, do_sample=True, temperature=0.3
),
)
|