Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
library_name: transformers
|
5 |
+
datasets:
|
6 |
+
- nilq/babylm-10M
|
7 |
+
---
|
8 |
+
|
9 |
+
- GPT-2 model trained as ablation by team CLAUSE Bielefeld for the BabyLM challenge 2023
|
10 |
+
- for more info, please check out the paper
|
11 |
+
|
12 |
+
Citation:
|
13 |
+
```
|
14 |
+
@inproceedings{bunzeck-zarriess-2023-gpt,
|
15 |
+
title = "{GPT}-wee: How Small Can a Small Language Model Really Get?",
|
16 |
+
author = "Bunzeck, Bastian and
|
17 |
+
Zarrie{\ss}, Sina",
|
18 |
+
editor = "Warstadt, Alex and
|
19 |
+
Mueller, Aaron and
|
20 |
+
Choshen, Leshem and
|
21 |
+
Wilcox, Ethan and
|
22 |
+
Zhuang, Chengxu and
|
23 |
+
Ciro, Juan and
|
24 |
+
Mosquera, Rafael and
|
25 |
+
Paranjabe, Bhargavi and
|
26 |
+
Williams, Adina and
|
27 |
+
Linzen, Tal and
|
28 |
+
Cotterell, Ryan",
|
29 |
+
booktitle = "Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning",
|
30 |
+
month = dec,
|
31 |
+
year = "2023",
|
32 |
+
address = "Singapore",
|
33 |
+
publisher = "Association for Computational Linguistics",
|
34 |
+
url = "https://aclanthology.org/2023.conll-babylm.2",
|
35 |
+
doi = "10.18653/v1/2023.conll-babylm.2",
|
36 |
+
pages = "35--46",
|
37 |
+
}
|
38 |
+
|
39 |
+
```
|