Last active
November 12, 2024 17:34
-
-
Save bigsnarfdude/ee1435eba1f23d1dfcefeb39d063a70d to your computer and use it in GitHub Desktop.
llama3.2-vision.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import ollama | |
target_images = ['1.jpg'] | |
questions = [ 'What is in this image?', | |
'Is this a slide show presentation?', | |
'Is the person teaching? (YES/NO): ', | |
'Is a person drawing on the green chalk board? (YES/NO): ', | |
'Is a person in the scene? (YES/NO): ' | |
] | |
for question_text in questions: | |
response = ollama.chat( | |
model='llama3.2-vision', | |
messages=[{ | |
'role': 'user', | |
'content': question_text, | |
'images': target_images | |
}] | |
) | |
print(response) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I apologize for the mistake earlier. There are no cats in this image, only a collage of nine different colored backgrounds
with a cat face superimposed over each one.