|
--- |
|
license: llama3.2 |
|
datasets: |
|
- CarrotAI/Magpie-Ko-Pro-AIR |
|
- CarrotAI/Carrot |
|
- CarrotAI/ko-instruction-dataset |
|
language: |
|
- ko |
|
- en |
|
base_model: |
|
- meta-llama/Llama-3.2-3B-Instruct |
|
pipeline_tag: text-generation |
|
new_version: CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412 |
|
--- |
|
|
|
![image/webp](https://cdn-uploads.huggingface.co/production/uploads/64633ebb39359568c63b52ad/VMYmYpoc0pQVSgZI0kme0.webp) |
|
|
|
## Model Description |
|
|
|
### Model Details |
|
- **Name**: Carrot Llama-3.2 Rabbit Ko |
|
- **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 |
|
|
|
### 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") |
|
tokenizer = AutoTokenizer.from_pretrained("CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct") |
|
``` |
|
|
|
## Score |
|
|
|
|Tasks|Version| Filter |n-shot| Metric | |Value | |Stderr| |
|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:| |
|
|gsm8k| 3|flexible-extract| 5|exact_match|โ |0.6490|ยฑ |0.0131| |
|
| | |strict-match | 5|exact_match|โ |0.0023|ยฑ |0.0013| |
|
|gsm8k-ko| 3|flexible-extract| 5|exact_match|โ |0.3275|ยฑ |0.0134| |
|
| | |strict-match | 5|exact_match|โ |0.2737|ยฑ |0.0134| |
|
|ifeval| 4|none | 5|inst_level_loose_acc |โ |0.8058|ยฑ | N/A| |
|
| | |none | 5|inst_level_strict_acc |โ |0.7686|ยฑ | N/A| |
|
| | |none | 5|prompt_level_loose_acc |โ |0.7320|ยฑ |0.0191| |
|
| | |none | 5|prompt_level_strict_acc|โ |0.6858|ยฑ |0.0200| |
|
|
|
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr| |
|
|-------------------------------|------:|------|-----:|--------|---|-----:|---|-----:| |
|
|haerae | 1|none | |acc |โ |0.4180|ยฑ |0.0148| |
|
| | |none | |acc_norm|โ |0.4180|ยฑ |0.0148| |
|
| - haerae_general_knowledge | 1|none | 5|acc |โ |0.3125|ยฑ |0.0350| |
|
| | |none | 5|acc_norm|โ |0.3125|ยฑ |0.0350| |
|
| - haerae_history | 1|none | 5|acc |โ |0.3404|ยฑ |0.0347| |
|
| | |none | 5|acc_norm|โ |0.3404|ยฑ |0.0347| |
|
| - haerae_loan_word | 1|none | 5|acc |โ |0.4083|ยฑ |0.0379| |
|
| | |none | 5|acc_norm|โ |0.4083|ยฑ |0.0379| |
|
| - haerae_rare_word | 1|none | 5|acc |โ |0.4815|ยฑ |0.0249| |
|
| | |none | 5|acc_norm|โ |0.4815|ยฑ |0.0249| |
|
| - haerae_standard_nomenclature| 1|none | 5|acc |โ |0.4771|ยฑ |0.0405| |
|
| | |none | 5|acc_norm|โ |0.4771|ยฑ |0.0405| |
|
|
|
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr| |
|
|----------------|------:|------|-----:|--------|---|-----:|---|------| |
|
|kobest_boolq | 1|none | 5|acc |โ |0.7664|ยฑ |0.0113| |
|
| | |none | 5|f1 |โ |0.7662|ยฑ | N/A| |
|
|kobest_copa | 1|none | 5|acc |โ |0.5620|ยฑ |0.0157| |
|
| | |none | 5|f1 |โ |0.5612|ยฑ | N/A| |
|
|kobest_hellaswag| 1|none | 5|acc |โ |0.3840|ยฑ |0.0218| |
|
| | |none | 5|acc_norm|โ |0.4900|ยฑ |0.0224| |
|
| | |none | 5|f1 |โ |0.3807|ยฑ | N/A| |
|
|kobest_sentineg | 1|none | 5|acc |โ |0.5869|ยฑ |0.0247| |
|
| | |none | 5|f1 |โ |0.5545|ยฑ | N/A| |
|
|kobest_wic | 1|none | 5|acc |โ |0.4952|ยฑ |0.0141| |
|
| | |none | 5|f1 |โ |0.4000|ยฑ | N/A| |
|
|
|
|
|
``` |
|
@article{Llama3.2RabbitKo3BInstruct, |
|
title={CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct Card}, |
|
author={CarrotAI (L, GEUN)}, |
|
year={2024}, |
|
url = {https://huggingface.co/CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct} |
|
} |
|
``` |