README.md

---
tags:
    - text-generation
license: cc-by-nc-4.0
language:
    - ko
base_model: yanolja/Bookworm-10.7B-v0.4-DPO
pipeline_tag: text-generation
---

# **DataVortexS-10.7B-dpo-v1.4**

<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">

## Our Team

| Research & Engineering | Product Management |
| :--------------------: | :----------------: |
|     Kwangseok Yang     |   Seunghyun Choi   |
|     Jeongwon Choi      |    Hyoseok Choi    |

## **Model Details**

### **Base Model**

[yanolja/Bookworm-10.7B-v0.4-DPO](https://huggingface.co/yanolja/Bookworm-10.7B-v0.4-DPO)

### **Trained On**

-   **OS**: Ubuntu 22.04
-   **GPU**: H100 80GB 4ea
-   **transformers**: v4.36.2

### **Instruction format**

It follows **ChatML** format.

E.g.

```python
text = """\
<|im_start|>system
당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.<|im_end|>
<|im_start|>user
대한민국의 수도는 어디야?<|im_end|>
<|im_start|>assistant
대한민국의 수도는 서울입니다.<|im_end|>
<|im_start|>user
서울 인구는 총 몇 명이야?<|im_end|>
<|im_start|>assistant
"""
```

## **Model Benchmark**

### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**

| Task             |       0-shot |       5-shot |      10-shot |      50-shot |
| :--------------- | -----------: | -----------: | -----------: | -----------: |
| kobest_boolq     |     0.757911 |     0.907177 |     0.924496 |     0.605075 |
| kobest_copa      |     0.740605 |     0.801886 |     0.831886 |     0.849978 |
| kobest_hellaswag |     0.445176 |     0.454788 |     0.468654 |      0.45218 |
| kobest_sentineg  |     0.415445 |      0.95214 |     0.962217 |     0.967254 |
| **Average**      | **0.589784** | **0.778998** | **0.796813** | **0.718622** |

### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**

| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
|   53.81 |  52.05 |        62.93 |   53.59 |         50.42 |           50.06 |

## **Implementation Code**

This model contains the chat_template instruction format.  
You can use the code below.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.4")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.4")

messages = [
    {"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."},
    {"role": "user", "content": "대한민국의 수도는 어디야?"},
    {"role": "assistant", "content": "대한민국의 수도는 서울입니다."},
    {"role": "user", "content": "서울 인구는 총 몇 명이야?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```

## **License**

This model is licensed under the [cc-by-nc-4.0](https://creativecommons.org/licenses/by-nc/4.0/). which allows others to share and adapt the model for non-commercial purposes.

<div align="center">
    <a href="https://edentns.com/">
        <img src="./Logo.png" alt="Logo" style="height: 3em;">
    </a>
</div>