Instructions to use ishaangupta293/kosmos-2-patch14-24-dup-ms with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ishaangupta293/kosmos-2-patch14-24-dup-ms 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="ishaangupta293/kosmos-2-patch14-24-dup-ms")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("ishaangupta293/kosmos-2-patch14-24-dup-ms") model = AutoModelForImageTextToText.from_pretrained("ishaangupta293/kosmos-2-patch14-24-dup-ms") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 2d3d525376f8d34df79f8cfcbc4fdeb72c9745705ed6dd7c2e1dfbeb5fcd09de
- Size of remote file:
- 6.66 GB
- SHA256:
- 47e771fe58dd4de2d814655e67ec034b3637b09114869415f071486c4a1c2ec0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.