Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# Moonline
|
|
@@ -83,5 +84,4 @@ The model hallucinetes especially in cases where a field is given, that doesn't
|
|
| 83 |
This can be alleviated by giving `None` options or guidance in the prompt. But in my experience this doesn't solve the issue fully.
|
| 84 |
|
| 85 |
Moondream is also not specifically trained on json output. I expect results would be improved by fine-tuning on json descriptions of
|
| 86 |
-
images. Especially cases where missing fields are present.
|
| 87 |
-
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: image-to-text
|
| 4 |
---
|
| 5 |
|
| 6 |
# Moonline
|
|
|
|
| 84 |
This can be alleviated by giving `None` options or guidance in the prompt. But in my experience this doesn't solve the issue fully.
|
| 85 |
|
| 86 |
Moondream is also not specifically trained on json output. I expect results would be improved by fine-tuning on json descriptions of
|
| 87 |
+
images. Especially cases where missing fields are present.
|
|
|