Instructions to use getZuma/image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use getZuma/image-captioning 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="getZuma/image-captioning")# Load model directly from transformers import AutoProcessor, AutoModelForVisualQuestionAnswering processor = AutoProcessor.from_pretrained("getZuma/image-captioning") model = AutoModelForVisualQuestionAnswering.from_pretrained("getZuma/image-captioning") - Notebooks
- Google Colab
- Kaggle
Commit ·
317eeaa
1
Parent(s): 16a8334
spell fix
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ duplicated_from: Salesforce/blip2-opt-2.7b
|
|
| 12 |
|
| 13 |
# Update to existing Salesforce model card:
|
| 14 |
|
| 15 |
-
**Added handler to run
|
| 16 |
|
| 17 |
Input:
|
| 18 |
```
|
|
|
|
| 12 |
|
| 13 |
# Update to existing Salesforce model card:
|
| 14 |
|
| 15 |
+
**Added handler to run the model on hugging face inference pipeline.**
|
| 16 |
|
| 17 |
Input:
|
| 18 |
```
|