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")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/kosmos-2-patch14-224") model = AutoModelForMultimodalLM.from_pretrained("microsoft/kosmos-2-patch14-224", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Fix task tag
Verified signature1f66d91
-
Adding `safetensors` variant of this model (#6)
- Adding `safetensors` variant of this model (9c090f58843c736a67353d8b8880f216aece5598) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>e91cfbc
-
Update README.md
823ed9f -
Update README.md
bd2073f -
Update README.md
3b7830b -
Update README.md
1c64239 -
Update README.md
cd1decd -
Update README.md
ab617dd -
Upload annotated_snowman.jpg
0f4a050 -
Update README.md
2fd86d6 -
Update README.md
cf00608 -
Create README.md
6016943
-
Upload processor
8bc83fb -
Upload processor
aaa2bff
-
Upload 3 files
bfbdbb7 -
Upload processor
49a13f7 -
Upload processor
a6fb1e5 -
Upload processor
042079d
-
Upload Kosmos2ForConditionalGeneration
89abd7d -
initial commit
c40cf6f