Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,37 @@ new_version: CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412
|
|
| 15 |
|
| 16 |

|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
## Score
|
| 19 |
|
| 20 |
|Tasks|Version| Filter |n-shot| Metric | |Value | |Stderr|
|
|
|
|
| 15 |
|
| 16 |

|
| 17 |
|
| 18 |
+
## Model Description
|
| 19 |
+
|
| 20 |
+
### Model Details
|
| 21 |
+
- **Name**: Carrot Llama-3.2 Rabbit Ko
|
| 22 |
+
- **Version**: 3B Instruct
|
| 23 |
+
- **Base Model**: CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct
|
| 24 |
+
- **Languages**: Korean, English
|
| 25 |
+
- **Model Type**: Large Language Model (Instruction-tuned)
|
| 26 |
+
|
| 27 |
+
### Training Process
|
| 28 |
+
๋ณธ ๋ชจ๋ธ์ ๋ค์๊ณผ ๊ฐ์ ์ฃผ์ ํ๋ จ ๋จ๊ณ๋ฅผ ๊ฑฐ์ณค์ต๋๋ค:
|
| 29 |
+
|
| 30 |
+
1. **SFT (Supervised Fine-Tuning)**
|
| 31 |
+
- ๊ณ ํ์ง ํ๊ตญ์ด ๋ฐ ์์ด ๋ฐ์ดํฐ์
์ ์ฌ์ฉํ์ฌ ๊ธฐ๋ณธ ๋ชจ๋ธ์ ์ธ๋ถ ์กฐ์
|
| 32 |
+
|
| 33 |
+
### Limitations
|
| 34 |
+
- 3B ํ๋ผ๋ฏธํฐ ๊ท๋ชจ๋ก ์ธํ ๋ณต์กํ ์์
์์์ ์ ํ์ ์ฑ๋ฅ
|
| 35 |
+
- ํน์ ๋๋ฉ์ธ์ ๋ํ ๊น์ด ์๋ ์ ๋ฌธ์ฑ ๋ถ์กฑ
|
| 36 |
+
- ํธํฅ์ฑ ๋ฐ ํ๊ฐ ๊ฐ๋ฅ์ฑ
|
| 37 |
+
|
| 38 |
+
### Ethics Statement
|
| 39 |
+
๋ชจ๋ธ ๊ฐ๋ฐ ๊ณผ์ ์์ ์ค๋ฆฌ์ ๊ณ ๋ ค์ฌํญ์ ์ต๋ํ ๋ฐ์ํ์์ผ๋, ์ฌ์ฉ์๋ ํญ์ ๊ฒฐ๊ณผ๋ฅผ ๋นํ์ ์ผ๋ก ๊ฒํ ํด์ผ ํฉ๋๋ค.
|
| 40 |
+
|
| 41 |
+
### How to Use
|
| 42 |
+
```python
|
| 43 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 44 |
+
|
| 45 |
+
model = AutoModelForCausalLM.from_pretrained("CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct")
|
| 46 |
+
tokenizer = AutoTokenizer.from_pretrained("CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct")
|
| 47 |
+
```
|
| 48 |
+
|
| 49 |
## Score
|
| 50 |
|
| 51 |
|Tasks|Version| Filter |n-shot| Metric | |Value | |Stderr|
|