|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- ko |
|
|
tags: |
|
|
- kaidol |
|
|
- ai-idol |
|
|
- character-ai |
|
|
- kto |
|
|
- conversational |
|
|
base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503 |
|
|
--- |
|
|
|
|
|
# KAIdol ์ฐจ๋ํ KTO |
|
|
|
|
|
KAIdol ์ฐจ๋ํ ์บ๋ฆญํฐ KTO ๋ชจ๋ธ (๋ฌด์ฌ๋ฌ, ISTP) |
|
|
|
|
|
## Model Description |
|
|
|
|
|
KAIdol ํ๋ก์ ํธ์ AI ์์ด๋ ์บ๋ฆญํฐ ๋ชจ๋ธ์
๋๋ค. |
|
|
KTO (Kahneman-Tversky Optimization) ๋ฐฉ๋ฒ๋ก ์ผ๋ก ์บ๋ฆญํฐ ์ผ๊ด์ฑ์ ๊ฐํํ์ต๋๋ค. |
|
|
|
|
|
### ์บ๋ฆญํฐ ์ ๋ณด |
|
|
- **์ด๋ฆ**: ์ฐจ๋ํ |
|
|
- **์ฑ๊ฒฉ**: ๋ฌด์ฌ๋ฌ (ISTP) |
|
|
- **ํน์ฑ**: ์ฟจํ๊ณ ๋ด๋ดํจ, ์ ์ ๋ ์ ์ ํํ |
|
|
- **๋งํฌ**: ์งง๊ณ ๋ด๋ฐฑํ ๋งํฌ |
|
|
|
|
|
## Training |
|
|
|
|
|
- **Base Model**: Mistral-Small-3.1-24B-Instruct-2503 |
|
|
- **Method**: KTO (Kahneman-Tversky Optimization) |
|
|
- **Framework**: TRL (Transformers Reinforcement Learning) |
|
|
- **Data**: LLM-as-Judge (RLAIF) ๊ธฐ๋ฐ ํ๊ฐ ๋ฐ์ดํฐ |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("developer-lunark/doha-kto") |
|
|
tokenizer = AutoTokenizer.from_pretrained("developer-lunark/doha-kto") |
|
|
|
|
|
messages = [ |
|
|
{"role": "system", "content": "๋น์ ์ KAIdol์ AI ์์ด๋ '์ฐจ๋ํ'์
๋๋ค."}, |
|
|
{"role": "user", "content": "์ค๋ ๊ธฐ๋ถ ์ด๋?"} |
|
|
] |
|
|
|
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
|
inputs = tokenizer(text, return_tensors="pt") |
|
|
output = model.generate(**inputs, max_new_tokens=200) |
|
|
print(tokenizer.decode(output[0], skip_special_tokens=True)) |
|
|
``` |
|
|
|
|
|
## License |
|
|
|
|
|
Apache 2.0 |
|
|
|