Instructions to use michelecafagna26/git-base-captioning-ft-hl-scenes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use michelecafagna26/git-base-captioning-ft-hl-scenes 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="michelecafagna26/git-base-captioning-ft-hl-scenes")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("michelecafagna26/git-base-captioning-ft-hl-scenes") model = AutoModelForImageTextToText.from_pretrained("michelecafagna26/git-base-captioning-ft-hl-scenes") - Notebooks
- Google Colab
- Kaggle
Commit ·
77d77dd
1
Parent(s): 3fb1c89
Update README.md
Browse files
README.md
CHANGED
|
@@ -63,4 +63,12 @@ processor.batch_decode(generated_ids, skip_special_tokens=True)
|
|
| 63 |
## BibTex and citation info
|
| 64 |
|
| 65 |
```BibTeX
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
```
|
|
|
|
| 63 |
## BibTex and citation info
|
| 64 |
|
| 65 |
```BibTeX
|
| 66 |
+
@inproceedings{cafagna2023hl,
|
| 67 |
+
title={{HL} {D}ataset: {V}isually-grounded {D}escription of {S}cenes, {A}ctions and
|
| 68 |
+
{R}ationales},
|
| 69 |
+
author={Cafagna, Michele and van Deemter, Kees and Gatt, Albert},
|
| 70 |
+
booktitle={Proceedings of the 16th International Natural Language Generation Conference (INLG'23)},
|
| 71 |
+
address = {Prague, Czech Republic},
|
| 72 |
+
year={2023}
|
| 73 |
+
}
|
| 74 |
```
|