24 lines
704 B
Python
24 lines
704 B
Python
# https://huggingface.co/allenai/olmOCR-7B-0225-preview
|
|
import torch
|
|
import base64
|
|
|
|
from io import BytesIO
|
|
from PIL import image
|
|
from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
|
|
|
|
from olmocr.data.renderpdf import render_pdf_to_base64png
|
|
from olmocr.prompts import build_finetuning_prompt
|
|
from olmocr.prompts.anchor import get_anchor_text
|
|
|
|
|
|
# Initialize the model
|
|
model = Qwen2VLForConditionalGeneration.from_pretrained("allenai/olmOCR-7B-0225-preview", torch_dtype=torch.bfloat16).eval()
|
|
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
model.to(device)
|
|
|
|
#for all pages in a pdf
|
|
for
|
|
|
|
#
|