git-base-instagram-cap

This model is a fine-tuned version of microsoft/git-base on an mrSoul7766/instagram_post_captions.

It achieves the following results on the evaluation set:

• Loss: 0.0093

Usage

you can leverage the capabilities provided by the Hugging Face Transformers library. Here's a basic example using Python:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-to-text", model="mrSoul7766/git-base-instagram-cap")

# Generate caption
caption = pipe("/content/download (12).png",max_new_tokens =100)

# Print the generated answer
print(caption[0]['generated_text'])

i love my blonde character in kim kardashian hollywood! i'm playing now who's playing with me?

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0