ToddGoldfarb
commited on
Commit
•
623134a
1
Parent(s):
2bb3bfd
Update README.md
Browse files
README.md
CHANGED
@@ -6,7 +6,7 @@ language:
|
|
6 |
- en
|
7 |
pipeline_tag: conversational
|
8 |
---
|
9 |
-
|
10 |
|
11 |
Inspired by Allen AI's **Cosmo-XL**, **Cadet-Tiny** is a _very small_ conversational model trained off of the **SODA** dataset. **Cadet-Tiny** is intended for inference at the edge (on something as small as a 2GB RAM Raspberry Pi).
|
12 |
|
@@ -18,13 +18,13 @@ If you have any questions, or any comments on improvements, please contact me at
|
|
18 |
|
19 |
|
20 |
|
21 |
-
|
22 |
|
23 |
Here is the link to the Google Colab file, where I walk through the process of training the model and using the SODA public dataset from AI2.
|
24 |
|
25 |
https://colab.research.google.com/drive/1cx3Yujr_jGQkseqzXZW-2L0vEyEjds_s?usp=sharing
|
26 |
|
27 |
-
|
28 |
|
29 |
Use the code snippet below to get started with Cadet-Tiny!
|
30 |
|
@@ -134,7 +134,7 @@ if __name__ == '__main__':
|
|
134 |
main()
|
135 |
```
|
136 |
|
137 |
-
|
138 |
Special thanks to Hyunwoo Kim for discussing with me the best way to use the SODA dataset. If you haven't looked into their work with SODA, Prosocial-Dialog, or COSMO, I recommend you do so! As well, read the paper on SODA!
|
139 |
The article is listed below.
|
140 |
|
|
|
6 |
- en
|
7 |
pipeline_tag: conversational
|
8 |
---
|
9 |
+
# What is Cadet-Tiny?
|
10 |
|
11 |
Inspired by Allen AI's **Cosmo-XL**, **Cadet-Tiny** is a _very small_ conversational model trained off of the **SODA** dataset. **Cadet-Tiny** is intended for inference at the edge (on something as small as a 2GB RAM Raspberry Pi).
|
12 |
|
|
|
18 |
|
19 |
|
20 |
|
21 |
+
# Google Colab Link
|
22 |
|
23 |
Here is the link to the Google Colab file, where I walk through the process of training the model and using the SODA public dataset from AI2.
|
24 |
|
25 |
https://colab.research.google.com/drive/1cx3Yujr_jGQkseqzXZW-2L0vEyEjds_s?usp=sharing
|
26 |
|
27 |
+
# Get Started With Cadet-Tiny
|
28 |
|
29 |
Use the code snippet below to get started with Cadet-Tiny!
|
30 |
|
|
|
134 |
main()
|
135 |
```
|
136 |
|
137 |
+
# Citations and Special Thanks
|
138 |
Special thanks to Hyunwoo Kim for discussing with me the best way to use the SODA dataset. If you haven't looked into their work with SODA, Prosocial-Dialog, or COSMO, I recommend you do so! As well, read the paper on SODA!
|
139 |
The article is listed below.
|
140 |
|