---
libray_name: transformers
pipeline_tag: text-generation
license: other
license_name: llama3
license_link: LICENSE
language:
- ko
- en
tags:
- meta
- llama
- llama-3
- akallama
library_name: transformers
---
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
  <img src="https://github.com/0110tpwls/project/blob/master/image_720.png?raw=true" width="40%"/>
</a>


# AKALLAMA

AkaLlama is a series of Korean language models designed for practical usability across a wide range of tasks.
The initial model, AkaLlama-v0.1, is a fine-tuned version of Meta-Llama-3-70b-Instruct. It has been trained on a custom mix of publicly available datasets curated by the MIR Lab.
Our goal is to explore cost-effective ways to adapt high-performing LLMs for specific use cases, such as different languages (e.g., Korean) or domains (e.g., organization-specific chatbots).

### Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub.

- **Developed by:** [Yonsei MIRLab](https://mirlab.yonsei.ac.kr/)
- **Language(s) (NLP):** Korean, English
- **License:** llama3
- **Finetuned from model:** [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)

## How to use

This repo provides full model weight files for AkaLlama-70B-v0.1.

# Use with transformers

See the snippet below for usage with Transformers:

```python
import transformers
import torch

model_id = "mirlab/AkaLlama-llama3-70b-v0.1"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="auto",
)

system_prompt = """
당신은 연세대학교 멀티모달 연구실 (MIR lab) 이 만든 대규모 언어 모델인 AkaLlama (아카라마) 입니다.\n다음 지침을 따르세요:\n1. 사용자가 별도로 요청하지 않는 한 항상 한글로 소통하세요.\n2. 유해하거나 비윤리적, 차별적, 위험하거나 불법적인 내용이 답변에 포함되어서는 안 됩니다.\n3. 질문이 말이 되지 않거나 사실에 부합하지 않는 경우 정답 대신 그 이유를 설명하세요. 질문에 대한 답을 모른다면 거짓 정보를 공유하지 마세요.\n4. 안전이나 윤리에 위배되지 않는 한 사용자의 모든 질문에 완전하고 포괄적으로 답변하세요.
"""

messages = [
    {"role": "system", "content": "system_prompt"},
    {"role": "user", "content": "네 이름은 뭐야?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```

## Training Details
### Training Procedure

We trained AkaLlama using a preference learning alignment algorithm called [Odds Ratio Preference Optimization (ORPO)](https://huggingface.co/papers/2403.07691).
Our training pipeline is almost identical to that of [HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1), aside from minor hyperparameter changes.
Please check out Huggingface's [alignment handbook](https://github.com/huggingface/alignment-handbook?tab=readme-ov-file) for further details, including the chat template. 

### Training Data

Detailed descriptions regarding training data will be announced later.

### Examples

<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
  <img src="https://github.com/0110tpwls/project/blob/master/image (8).png?raw=true" width="80%"/>
</a>

<details>
<summary><b>Math Solving[CLICK TO EXPAND]</b></summary>
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
  <img src="https://github.com/0110tpwls/project/blob/master/image (9).png?raw=true" width="80%"/>
</a>
</details>

<details>
<summary><b>Writting[CLICK TO EXPAND]</b></summary>
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
  <img src="https://github.com/0110tpwls/project/blob/master/image (13).png?raw=true" width="80%"/>
</a>

<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
  <img src="https://github.com/0110tpwls/project/blob/master/image (7).png?raw=true" width="80%"/>
</a>
</details>

<details>
<summary><b>Logical Reasoning[CLICK TO EXPAND]</b></summary>
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
  <img src="https://github.com/0110tpwls/project/blob/master/image (15).png?raw=true" width="80%"/>
</a>
</details>

<details>
<summary><b>Coding [CLICK TO EXPAND]</b></summary>
<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
  <img src="https://github.com/0110tpwls/project/blob/master/image (11).png?raw=true" width="80%"/>
</a>
</details>

You can find more examples at [our project page](https://yonsei-mir.github.io/AkaLLaMA-page)

## Special Thanks

- Data Center of the Department of Artificial Intelligence at Yonsei University for the computation resources