jisukim8873
commited on
Commit
•
1e628df
1
Parent(s):
ee67cda
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- Open-Orca/SlimOrca
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
---
|
8 |
+
|
9 |
+
# Model Details
|
10 |
+
* Model Description: This model is test for data ordering.
|
11 |
+
* Developed by: Jisu Kim
|
12 |
+
* Model Type: Large Language Model
|
13 |
+
|
14 |
+
# Model Architecture
|
15 |
+
This model is based on falcon-7B. We fine-tuning this model for data ordering task.
|
16 |
+
|
17 |
+
falcon-7B is a transformer model, with the following architecture choices:
|
18 |
+
|
19 |
+
* Grouped-Query Attention
|
20 |
+
* Sliding-Window Attention
|
21 |
+
* Byte-fallback BPE tokenizer
|
22 |
+
|
23 |
+
# Dataset
|
24 |
+
We random sample Open-Orca dataset. (We finetune the 100,000 dataset)
|
25 |
+
|
26 |
+
# Guthub
|
27 |
+
https://github.com/trailerAI
|
28 |
+
|
29 |
+
# License
|
30 |
+
Apache License 2.0
|