Image-to-Text
Transformers
Safetensors
English
vision-encoder-decoder
image-text-to-text
vit
bert
vision
caption
captioning
image
Instructions to use cnmoro/mini-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cnmoro/mini-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="cnmoro/mini-image-captioning")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("cnmoro/mini-image-captioning") model = AutoModelForImageTextToText.from_pretrained("cnmoro/mini-image-captioning") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ tags:
|
|
| 15 |
- captioning
|
| 16 |
- image
|
| 17 |
---
|
| 18 |
-
An image captioning model, based on bert-mini and vit-small, weighing only
|
| 19 |
|
| 20 |
Works very fast on CPU.
|
| 21 |
|
|
|
|
| 15 |
- captioning
|
| 16 |
- image
|
| 17 |
---
|
| 18 |
+
An image captioning model, based on bert-mini and vit-small, weighing only 130mb!
|
| 19 |
|
| 20 |
Works very fast on CPU.
|
| 21 |
|