ayoubkirouane
commited on
Commit
·
84a5c10
1
Parent(s):
e036794
Update README.md
Browse files
README.md
CHANGED
@@ -23,7 +23,7 @@ datasets:
|
|
23 |
|
24 |
|
25 |
## Model Description
|
26 |
-
**Git-base-One-Piece** is a fine-tuned variant of Microsoft's **git-base** model, specifically trained for the task of generating descriptive text captions for images from the **One-Piece-anime-captions**
|
27 |
|
28 |
The dataset consists of **856 {image: caption}** pairs, providing a substantial and diverse training corpus for the model.
|
29 |
|
@@ -33,7 +33,7 @@ The model is conditioned on both CLIP image tokens and text tokens and employs a
|
|
33 |
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6338c06c107c4835a05699f9/N_yNK2tLabtwmSYAqpTEp.jpeg)
|
34 |
|
35 |
## Limitations
|
36 |
-
+ The quality of generated captions may vary depending on the complexity and diversity of images from the
|
37 |
+ The model's output is based on the data it was fine-tuned on, so it may not generalize well to images outside the dataset's domain.
|
38 |
Generating highly detailed or contextually accurate captions may still be a challenge.
|
39 |
|
|
|
23 |
|
24 |
|
25 |
## Model Description
|
26 |
+
**Git-base-One-Piece** is a fine-tuned variant of Microsoft's **git-base** model, specifically trained for the task of generating descriptive text captions for images from the **One-Piece-anime-captions** dataset.
|
27 |
|
28 |
The dataset consists of **856 {image: caption}** pairs, providing a substantial and diverse training corpus for the model.
|
29 |
|
|
|
33 |
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6338c06c107c4835a05699f9/N_yNK2tLabtwmSYAqpTEp.jpeg)
|
34 |
|
35 |
## Limitations
|
36 |
+
+ The quality of generated captions may vary depending on the complexity and diversity of images from the **One-Piece-anime-captions** dataset.
|
37 |
+ The model's output is based on the data it was fine-tuned on, so it may not generalize well to images outside the dataset's domain.
|
38 |
Generating highly detailed or contextually accurate captions may still be a challenge.
|
39 |
|