|
--- |
|
license: llama3.2 |
|
datasets: |
|
- CarrotAI/Carrot |
|
- CarrotAI/Chat-Template |
|
language: |
|
- ko |
|
- en |
|
base_model: |
|
- CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
 |
|
|
|
## Model Description |
|
|
|
### Model Details |
|
- **Name**: Carrot Llama-3.2 Rabbit Ko 2412 |
|
- **Version**: 3B Instruct |
|
- **Base Model**: CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct |
|
- **Languages**: Korean, English |
|
- **Model Type**: Large Language Model (Instruction-tuned) |
|
|
|
### Training Process |
|
๋ณธ ๋ชจ๋ธ์ ๋ค์๊ณผ ๊ฐ์ ์ฃผ์ ํ๋ จ ๋จ๊ณ๋ฅผ ๊ฑฐ์ณค์ต๋๋ค: |
|
|
|
1. **SFT (Supervised Fine-Tuning)** |
|
- ๊ณ ํ์ง ํ๊ตญ์ด ๋ฐ ์์ด ๋ฐ์ดํฐ์
์ ์ฌ์ฉํ์ฌ ๊ธฐ๋ณธ ๋ชจ๋ธ์ ์ธ๋ถ ์กฐ์ |
|
|
|
2. **DPO (Direct Preference Optimization)** |
|
- ์ธ๊ฐ์ ์ ํธ๋๋ฅผ ์ง์ ์ ์ผ๋ก ๋ฐ์ํ์ฌ ๋ชจ๋ธ์ ์๋ต ํ์ง ๊ฐ์ |
|
|
|
### Limitations |
|
- 3B ํ๋ผ๋ฏธํฐ ๊ท๋ชจ๋ก ์ธํ ๋ณต์กํ ์์
์์์ ์ ํ์ ์ฑ๋ฅ |
|
- ํน์ ๋๋ฉ์ธ์ ๋ํ ๊น์ด ์๋ ์ ๋ฌธ์ฑ ๋ถ์กฑ |
|
- ํธํฅ์ฑ ๋ฐ ํ๊ฐ ๊ฐ๋ฅ์ฑ |
|
|
|
### Ethics Statement |
|
๋ชจ๋ธ ๊ฐ๋ฐ ๊ณผ์ ์์ ์ค๋ฆฌ์ ๊ณ ๋ ค์ฌํญ์ ์ต๋ํ ๋ฐ์ํ์์ผ๋, ์ฌ์ฉ์๋ ํญ์ ๊ฒฐ๊ณผ๋ฅผ ๋นํ์ ์ผ๋ก ๊ฒํ ํด์ผ ํฉ๋๋ค. |
|
|
|
### How to Use |
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model = AutoModelForCausalLM.from_pretrained("CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412") |
|
tokenizer = AutoTokenizer.from_pretrained("CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412") |
|
``` |
|
|
|
## Score |
|
### Performance Metrics |
|
LogicKor |
|
| Category | Single turn | Multi turn | |
|
|---|---|---| |
|
| ์ํ(Math) | 5.86 | 5.14 | |
|
| ๋ฌธ๋ฒ(Grammar) | 4.71 | 1.29 | |
|
| ์ดํด(Understanding) | 4.00 | 4.43 | |
|
| ์ถ๋ก (Reasoning) | 5.14 | 6.71 | |
|
| ์ฝ๋ฉ(Coding) | 7.43 | 7.57 | |
|
| ๊ธ์ฐ๊ธฐ(Writing) | 8.43 | 8.00 | |
|
| **Total** | **5.93** | **5.52** | |
|
| **Overall** | **5.73** | | |
|
|
|
|
|
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr| |
|
|--------|------:|----------------|-----:|-----------------------|---|-----:|---|------| |
|
|gsm8k | 3|flexible-extract| 5|exact_match |โ |0.7013|ยฑ |0.0126| |
|
| | |strict-match | 5|exact_match |โ |0.2418|ยฑ |0.0118| |
|
|gsm8k-ko| 1|flexible-extract| 5|exact_match |โ |0.4466|ยฑ |0.0137| |
|
| | |strict-match | 5|exact_match |โ |0.4420|ยฑ |0.0137| |
|
|ifeval | 4|none | 0|inst_level_loose_acc |โ |0.8549|ยฑ | N/A| |
|
| | |none | 0|inst_level_strict_acc |โ |0.8225|ยฑ | N/A| |
|
| | |none | 0|prompt_level_loose_acc |โ |0.7874|ยฑ |0.0176| |
|
| | |none | 0|prompt_level_strict_acc|โ |0.7468|ยฑ |0.0187| |
|
|
|
|
|
|Task|Score|shot| |
|
|---|---|---| |
|
|haerae|43.26|5| |
|
|
|
``` |
|
@article{Llama3.2RabbitKo3BInstruct, |
|
title={CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412 Card}, |
|
author={CarrotAI (L, GEUN)}, |
|
year={2024}, |
|
url = {https://huggingface.co/CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412} |
|
} |
|
``` |