Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,49 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
+
language:
|
4 |
+
- ko
|
5 |
+
library_name: transformers
|
6 |
+
pipeline_tag: text-generation
|
7 |
---
|
8 |
+
|
9 |
+
|
10 |
+
**The license is `cc-by-nc-4.0`.**
|
11 |
+
|
12 |
+
# **GAI-LLM/Llama-3-8B_classification**
|
13 |
+
|
14 |
+
## Model Details
|
15 |
+
|
16 |
+
**Model Developers** Donghoon Oh, Hanmin Myung, SuKyung Park (SK C&C G.AI Eng)
|
17 |
+
|
18 |
+
**Input** Models input text only.
|
19 |
+
|
20 |
+
**Output** Models generate text only.
|
21 |
+
|
22 |
+
**Model Architecture**
|
23 |
+
GAI-LLM/Llama-3-8B_classification is an auto-regressive language model based on the LLaMA2 transformer architecture.
|
24 |
+
|
25 |
+
**Base Model** [meta-llama/Meta-Llama-3-8B]
|
26 |
+
|
27 |
+
**Training Dataset**
|
28 |
+
|
29 |
+
- We combined Open Korean Dateset using mixed-strategy
|
30 |
+
- We use A100 GPU 80GB * 8, when training.
|
31 |
+
|
32 |
+
# **Model Benchmark**
|
33 |
+
|
34 |
+
|
35 |
+
# Implementation Code
|
36 |
+
```python
|
37 |
+
### GAI-LLM/Llama-3-8B_classification
|
38 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
39 |
+
import torch
|
40 |
+
|
41 |
+
repo = "GAI-LLM/Llama-3-8B_classification"
|
42 |
+
model = AutoModelForCausalLM.from_pretrained(
|
43 |
+
repo,
|
44 |
+
return_dict=True,
|
45 |
+
torch_dtype=torch.float16,
|
46 |
+
device_map='auto'
|
47 |
+
)
|
48 |
+
tokenizer = AutoTokenizer.from_pretrained(repo)
|
49 |
+
```
|