Instructions to use Salesforce/blip-image-captioning-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-image-captioning-large with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large") model = AutoModelForImageTextToText.from_pretrained("Salesforce/blip-image-captioning-large") - Notebooks
- Google Colab
- Kaggle
How to train model with custom data?
#27
by Hirobi07 - opened
I would like to train this model with my custom data. Can I do that?
Hi @Hirobi07
Yes, this is possible, you can read this thread: https://discuss.huggingface.co/t/finetune-blip-on-customer-dataset-20893/28446 for more details on how to do it
Hi @Hirobi07
Yes, this is possible, you can read this thread: https://discuss.huggingface.co/t/finetune-blip-on-customer-dataset-20893/28446 for more details on how to do it
Hello!
This is a fine-tuning performed on the VQA dataset. How can I perform fine-tuning on the dataset of the image captioning task?