Instructions to use microsoft/kosmos-2-patch14-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/kosmos-2-patch14-224 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="microsoft/kosmos-2-patch14-224")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("microsoft/kosmos-2-patch14-224") model = AutoModelForImageTextToText.from_pretrained("microsoft/kosmos-2-patch14-224") - Notebooks
- Google Colab
- Kaggle
how to use downloaded model in my local
#13
by karambos - opened
This comment has been hidden
model = AutoModelForVision2Seq.from_pretrained("microsoft/kosmos-2-patch14-224", cache_dir = ".cache/", device_map = "auto")
processor = AutoProcessor.from_pretrained("microsoft/kosmos-2-patch14-224", cache_dir = ".cache/")
if I run this code but the model is downloading in the local but model is already downloaded in my local already
My mistake actually i define the wrong path
karambos changed discussion status to closed