ozcangundes
commited on
Commit
•
226d127
1
Parent(s):
5aecbb1
Update README.md
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ license: MIT
|
|
10 |
|
11 |
[Google's Multilingual T5-small](https://github.com/google-research/multilingual-t5) is fine-tuned on [Turkish Question Answering dataset](https://github.com/TQuad/turkish-nlp-qa-dataset) for **Q&A** downstream task by using Pytorch Lightning.⚡
|
12 |
|
13 |
-
The notebook that includes all fine tuning process will be shared on my Github page later.
|
14 |
|
15 |
**Important Note**: mT5 was only pre-trained on [mC4](https://www.tensorflow.org/datasets/catalog/c4#c4multilingual)
|
16 |
excluding any supervised training. Therefore, the mT5 model has to be fine-tuned before it is useable on a downstream task.
|
|
|
10 |
|
11 |
[Google's Multilingual T5-small](https://github.com/google-research/multilingual-t5) is fine-tuned on [Turkish Question Answering dataset](https://github.com/TQuad/turkish-nlp-qa-dataset) for **Q&A** downstream task by using Pytorch Lightning.⚡
|
12 |
|
13 |
+
The notebook that includes all fine tuning process will be shared on my Github page later. mT5 small model has 300 million parameters and model size is about 1.2GB. Therefore, it takes significant amount of time to fine tune it.
|
14 |
|
15 |
**Important Note**: mT5 was only pre-trained on [mC4](https://www.tensorflow.org/datasets/catalog/c4#c4multilingual)
|
16 |
excluding any supervised training. Therefore, the mT5 model has to be fine-tuned before it is useable on a downstream task.
|