---
license: cc-by-nc-4.0
language:
- ko
---

### Developed by Jaeyeon Kang ([CCK Solution](https://www.ccksolution.co.kr/))

## Model Description
- This is a model for the korean language.
- We fine-tuned this model based on [ShinojiResearch/Senku-70B-Full](https://huggingface.co/ShinojiResearch/Senku-70B-Full) with our training dataset(private).
- DPO (QLoRA) training are adjusted .

## Run the model


```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "JaeyeonKang/CCK-Asura-v3"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id)

text = "[INST] Put instruction here. [/INST]"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```