Ashokajou51
commited on
Commit
•
63e637d
1
Parent(s):
ebc054d
Update README.md
Browse files
README.md
CHANGED
@@ -11,17 +11,12 @@ tags:
|
|
11 |
- nontoxicbert
|
12 |
---
|
13 |
|
14 |
-
|
15 |
-
prediction less toxic.
|
16 |
|
17 |
-
|
|
|
18 |
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
from transformers import AutoTokenizer, AutoModelForMaskedLM
|
24 |
-
|
25 |
-
tokenizer = AutoTokenizer.from_pretrained("Ashokajou51/NonToxicCivilBert")
|
26 |
-
|
27 |
-
model = AutoModelForMaskedLM.from_pretrained("Ashokajou51/NonToxicCivilBert")
|
|
|
11 |
- nontoxicbert
|
12 |
---
|
13 |
|
14 |
+
# Description
|
|
|
15 |
|
16 |
+
CivilBert is a further finetuned model of bert-based-uncased using only the non-toxic data of the Jigsaw-unintended-bias dataset to make the predicted tokens less toxic.
|
17 |
+
We are working further to make this model better and less toxic.
|
18 |
|
19 |
+
# You can use it directly using the transformers:
|
20 |
+
* from transformers import AutoTokenizer, AutoModelForMaskedLM
|
21 |
+
* tokenizer = AutoTokenizer.from_pretrained("Ashokajou51/NonToxicCivilBert")
|
22 |
+
* model = AutoModelForMaskedLM.from_pretrained("Ashokajou51/NonToxicCivilBert")
|
|
|
|
|
|
|
|
|
|