Instructions to use captioner/caption-gen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use captioner/caption-gen 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="captioner/caption-gen")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("captioner/caption-gen") model = AutoModelForMultimodalLM.from_pretrained("captioner/caption-gen") - Notebooks
- Google Colab
- Kaggle
Devin Zhang commited on
Commit ·
95a21c2
1
Parent(s): 9d36b15
Delete training_args.bin
Browse files- training_args.bin +0 -3
training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a3e26e6a6871ccf28a8e559f5bee16626b1fdd2d95de041a8098d47130ff7207
|
| 3 |
-
size 3899
|
|
|
|
|
|
|
|
|
|
|
|