bourdoiscatie
commited on
Commit
•
29f77dc
1
Parent(s):
4f41cdf
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,15 @@
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language: en
|
3 |
license: apache-2.0
|
4 |
---
|
5 |
+
|
6 |
+
### Description
|
7 |
+
Adaptation of the [flan-t5-xl](https://huggingface.co/google/flan-t5-xl) weights to make it compatible with the [FAT5](https://github.com/catie-aq/flashT5) framework (Flash Attention T5).
|
8 |
+
This adaptation should enable the user to efficiently continue the pre-training of the flan-t5 to adapt it to more recent data, or to specialize it in a specific domain, for example.
|
9 |
+
|
10 |
+
### Usage
|
11 |
+
```
|
12 |
+
from transformers import AutoModel, AutoTokenizer
|
13 |
+
model = AutoModel.from_pretrained("CATIE-AQ/FAT5-xl-flan-en", trust_remote_code=True)
|
14 |
+
tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-small")
|
15 |
+
```
|