---
language:
- ko
datasets:
- kyujinpy/KOpen-platypus
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
---

# **Kosy🍵llama**   
![img](./Koisy_llama.JPG)  

## Model Details

**Model Developers** Kyujin Han (kyujinpy)

**Model Description**  
[NEFTune](https://github.com/neelsjain/NEFTune) method를 활용하여 훈련한 Ko-platypus2 new version!  
(Noisy + KO + llama = Kosy🍵llama)

**Repo Link**  
Github **KoNEFTune**: [Kosy🍵llama](https://github.com/Marker-Inc-Korea/KoNEFTune)  
If you visit our github, you can easily apply **Random_noisy_embedding_fine-tuning**!!

**Base Model**   
[hyunseoki/ko-en-llama2-13b](https://huggingface.co/hyunseoki/ko-en-llama2-13b)   

**Training Dataset**  
Version of combined dataset: [kyujinpy/KOpen-platypus](https://huggingface.co/datasets/kyujinpy/KOpen-platypus)  
I use A100 GPU 40GB and COLAB, when trianing.  

# **Model comparisons**
[KO-LLM leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)  
# **NEFT comparisons**
![img](./comparison.png)  
| Model | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| --- | --- | --- | --- | --- | --- | --- |
| [Ko-Platypus2-13B](https://huggingface.co/kyujinpy/KO-Platypus2-13B) | 45.60 | 44.20 | 54.31 | 42.47 | 44.41 | 42.62 |
| *NEFT(🍵kosy)+MLP-v1 | 43.64 | 43.94 | 53.88 | 42.68 | 43.46 | 34.24 |   
| *NEFT(🍵kosy)+MLP-v2 | 45.45 | 44.20 | 54.56 | 42.60 | 42.68 | 42.98 |   
| [***NEFT(🍵kosy)+MLP-v3**](https://huggingface.co/kyujinpy/Kosy-platypus2-13B-v3) | 46.31 | 43.34 | 54.54 | 43.38 | 44.11 | 46.16 |  
| NEFT(🍵kosy)+Attention | 44.92 |42.92 | 54.48 | 42.99 | 43.00 | 41.20 |
| NEFT(🍵kosy) | 45.08 | 43.09 | 53.61 | 41.06 | 43.47 | 43.21 |  
> *Different Hyperparameters such that learning_rate, batch_size, epoch, etc...  
  
# Implementation Code
```python
### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "kyujinpy/Koisy-Platypus2-13B"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
```

---