Bram Vanroy
commited on
Commit
•
fbc7281
1
Parent(s):
d3a07ee
add information
Browse files
app.py
CHANGED
|
@@ -95,7 +95,19 @@ else:
|
|
| 95 |
########################
|
| 96 |
st.header("Project background")
|
| 97 |
|
| 98 |
-
st.markdown("""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
|
| 100 |
|
| 101 |
st.header("Contact ✒️")
|
|
|
|
| 95 |
########################
|
| 96 |
st.header("Project background")
|
| 97 |
|
| 98 |
+
st.markdown("""This demo highlights work that has been done in light of a master thesis by Charlotte Van de Velde as part of the Master of Science in Artificial Intelligence at KU Leuven in 2023. Charlotte is supervised by Vincent Vandeghinste and Bram Vanroy.
|
| 99 |
+
|
| 100 |
+
Charlotte created a [dataset](https://huggingface.co/datasets/BramVanroy/chatgpt-dutch-simplification) that contains Dutch sentences and their simplified equivalents with ChatGPT. Bram then trained a number of models on this new dataset.
|
| 101 |
+
|
| 102 |
+
The following models are available, all finetuned from the awesome Dutch T5 models by [Yeb Havinga](https://huggingface.co/yhavinga):
|
| 103 |
+
|
| 104 |
+
- [`BramVanroy/ul2-small-dutch-simplification-mai-2023`](https://huggingface.co/BramVanroy/ul2-small-dutch-simplification-mai-2023)
|
| 105 |
+
- [`BramVanroy/ul2-base-dutch-simplification-mai-2023`](https://huggingface.co/BramVanroy/ul2-base-dutch-simplification-mai-2023) (used in this demo)
|
| 106 |
+
- [`BramVanroy/ul2-large-dutch-simplification-mai-2023`](https://huggingface.co/BramVanroy/ul2-large-dutch-simplification-mai-2023)
|
| 107 |
+
|
| 108 |
+
The training code can be found on [Github](https://github.com/BramVanroy/mai-simplification-nl-2023#22-hyperparameter-sweep).
|
| 109 |
+
|
| 110 |
+
""")
|
| 111 |
|
| 112 |
|
| 113 |
st.header("Contact ✒️")
|