Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
license: cc-by-nc-4.0
|
6 |
+
---
|
7 |
+
|
8 |
+
# AISquare-Instruct-llama2-koen-13b-v0.9.24
|
9 |
+
|
10 |
+
## Model Details
|
11 |
+
|
12 |
+
**Developed by**
|
13 |
+
[Inswave Systems](https://www.inswave.com) UI Platform Team
|
14 |
+
|
15 |
+
**Method**
|
16 |
+
Using DPO method and SFT method
|
17 |
+
|
18 |
+
**Hardware**
|
19 |
+
We utilized an A100x4 * 1 for training our model
|
20 |
+
|
21 |
+
**Base Model**
|
22 |
+
[beomi/llama2-koen-13b](https://huggingface.co/beomi/llama-2-koen-13b)
|
23 |
+
|
24 |
+
|
25 |
+
# Implementation Code
|
26 |
+
```python
|
27 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
28 |
+
import torch
|
29 |
+
|
30 |
+
repo = "inswave/AISquare-Instruct-llama2-koen-13b-v0.9.24"
|
31 |
+
model = AutoModelForCausalLM.from_pretrained(
|
32 |
+
repo,
|
33 |
+
return_dict=True,
|
34 |
+
torch_dtype=torch.float16,
|
35 |
+
device_map='auto'
|
36 |
+
)
|
37 |
+
tokenizer = AutoTokenizer.from_pretrained(repo)
|
38 |
+
```
|
39 |
+
|
40 |
+
---
|