Update README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,8 @@ widget:
|
|
13 |
|
14 |
# kgourgou/bert-base-uncased-QA-classification
|
15 |
|
16 |
-
An experiment into classifying whether a pair of (question, answer) is valid.
|
|
|
17 |
|
18 |
Input must be formatted as
|
19 |
|
@@ -33,6 +34,7 @@ Examples:
|
|
33 |
- "question: What number comes after five? answer: four" -> this should be class 1 as the answer is a number (even if it's not the right number).
|
34 |
- "question: Which person is associated with Kanye West? answer: a tree" -> this should be class 0 as a tree is not a person.
|
35 |
|
|
|
36 |
## Base model details
|
37 |
|
38 |
The base model is bert-base-uncased. For this experiment, I only use the "squad" dataset after preprocessing it to bring it to the required format.
|
|
|
13 |
|
14 |
# kgourgou/bert-base-uncased-QA-classification
|
15 |
|
16 |
+
An experiment into classifying whether a pair of (question, answer) is valid. This is not a very good model at this point, but eventually such a
|
17 |
+
a model could help with RAG.
|
18 |
|
19 |
Input must be formatted as
|
20 |
|
|
|
34 |
- "question: What number comes after five? answer: four" -> this should be class 1 as the answer is a number (even if it's not the right number).
|
35 |
- "question: Which person is associated with Kanye West? answer: a tree" -> this should be class 0 as a tree is not a person.
|
36 |
|
37 |
+
|
38 |
## Base model details
|
39 |
|
40 |
The base model is bert-base-uncased. For this experiment, I only use the "squad" dataset after preprocessing it to bring it to the required format.
|