Commit
·
0e40df4
1
Parent(s):
a7fbe53
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,3 +6,14 @@ pipeline_tag: image-to-text
|
|
| 6 |
|
| 7 |
# Sky Scribe 🛰️✍️
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
# Sky Scribe 🛰️✍️
|
| 8 |
|
| 9 |
+
|
| 10 |
+
This model is a fine-tuning of Microsoft's [git](https://huggingface.co/microsoft/git-base), used to caption satellite images annotated by NASA Earth Observatory.
|
| 11 |
+
|
| 12 |
+
As a result, when prompted with satellite images that are from or resemble the images shared by NASA Earth, will return a short description of that phenomena,
|
| 13 |
+
including guesses to the location, date, and instrument used to capture that image. These are often hallucinations, leading to an important next step in this model's development,
|
| 14 |
+
where I can replace those guesses with additional metadata to serve as an input.
|
| 15 |
+
|
| 16 |
+
By consequence of this model being a fine-tuned version of a larger model, there is much behavior I cannot be sure is appropriate,
|
| 17 |
+
especially for images that are not satellite images.
|
| 18 |
+
Please use with caution.
|
| 19 |
+
|