Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- ko
|
4 |
+
- en
|
5 |
+
library_name: transformers
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
---
|
8 |
+
This model has been developed by KAIST ALIN Lab and OMNIOUS.AI - HyunseokLee, TaeyoungKim
|
9 |
+
|
10 |
+
Input Models input text only.
|
11 |
+
|
12 |
+
Output Models generate text only.
|
13 |
+
|
14 |
+
Model Architecture
|
15 |
+
ko-en-llama2-13b-aligned is an auto-regressive language model based on the LLaMA2 transformer architecture.
|
16 |
+
|
17 |
+
Base Model
|
18 |
+
hyunseoki/ko-en-llama2-13b
|
19 |
+
|
20 |
+
Training Dataset
|
21 |
+
Open dataset wiki and AIhub (English + Korean).
|
22 |
+
Supervised Finetuned with Instruction Dataset and aligned with Human Preference Dataset using DPO.
|