[Python] Error Running OCR with Qwen2.5-VL in Colab

I am trying to run the OCR functionality of Qwen2.5-VL by following the tutorial provided in this notebook: OCR Tutorial Notebook

However, I am encountering an error when attempting to execute the code. Here are the details:

Steps Taken:

• I opened the notebook in Google Colab using this link: Colab Notebook
• I followed the instructions in the notebook to set up the environment and run the OCR example.

Error Encountered:

text: <|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
Extract the key-value information in the format:{"company": "", "date": "", "address": "", "total": ""}<|vision_start|><|image_pad|><|vision_end|><|im_end|>
<|im_start|>assistant

---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-24-176a5a9fc203> in <cell line: 0>()
6
7 ## Use a local HuggingFace model to inference.
----> 8 response = inference(image_path, prompt)
9 display(Markdown(response))

27 frames
/usr/local/lib/python3.11/dist-packages/triton/backends/nvidia/driver.py in __call__(self, *args, **kwargs)
442
443 def __call__(self, *args, **kwargs):
--> 444 self.launch(*args, **kwargs)
445
446

ValueError: Pointer argument (at 0) cannot be accessed from Triton (cpu tensor?)




Additional Information:

Environment : Google Colab

Python Version : Default Colab version

Google Colab: https://colab.research.google.com/drive/1JR1Abv9ORIQZWcjm5-xdFM4zJo6hdp51?usp=sharing

Continue reading...