Pankaj Mathur
commited on
Commit
·
5921341
1
Parent(s):
76bad9d
Update README.md
Browse files
README.md
CHANGED
@@ -2,21 +2,23 @@
|
|
2 |
license: mit
|
3 |
language:
|
4 |
- en
|
5 |
-
library_name:
|
|
|
|
|
6 |
---
|
7 |
-
#
|
8 |
-
An Open_LLaMA-3B model trained on
|
9 |
|
10 |
|
11 |
# Dataset
|
12 |
|
13 |
-
We
|
14 |
|
15 |
-
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom
|
16 |
|
17 |
-
This helps student model aka
|
18 |
|
19 |
-
Please see below example usage how the **System** prompt is added before each
|
20 |
|
21 |
# Training
|
22 |
|
|
|
2 |
license: mit
|
3 |
language:
|
4 |
- en
|
5 |
+
library_name: transformers
|
6 |
+
datasets:
|
7 |
+
- psmathur/alpaca_orca
|
8 |
---
|
9 |
+
# Orca_alpaca_3b
|
10 |
+
An Open_LLaMA-3B model trained on explain tuned datasets, created using Instructions and Input from Alpaca datasets and applying Orca Research Paper dataset construction approaches.
|
11 |
|
12 |
|
13 |
# Dataset
|
14 |
|
15 |
+
We build explain tuned [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
|
16 |
|
17 |
+
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
|
18 |
|
19 |
+
This helps student model aka this model to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
|
20 |
|
21 |
+
Please see below example usage how the **System** prompt is added before each **instruction**.
|
22 |
|
23 |
# Training
|
24 |
|