Commit
•
b2c5c91
1
Parent(s):
578108e
Update README.md
Browse files
README.md
CHANGED
@@ -144,7 +144,7 @@ This is the [flan-t5-large](https://huggingface.co/google/flan-t5-large) model,
|
|
144 |
|
145 |
This model was trained using LoRA available through the [PEFT library](https://github.com/huggingface/peft).
|
146 |
|
147 |
-
NOTE: The
|
148 |
|
149 |
## Overview
|
150 |
**Language model:** flan-t5-large
|
|
|
144 |
|
145 |
This model was trained using LoRA available through the [PEFT library](https://github.com/huggingface/peft).
|
146 |
|
147 |
+
NOTE: The `<cls>` token must be manually added to the beginning of the question for this model to work properly. It uses the `<cls>` token to be able to make "no answer" predictions. The t5 tokenizer does not automatically add this special token which is why it is added manually.
|
148 |
|
149 |
## Overview
|
150 |
**Language model:** flan-t5-large
|