---
base_model:
- maywell/kiqu-70b
library_name: transformers
tags:
- mergekit
- merge
license: cc-by-sa-4.0
language:
- ko
---
# Megakiqu-120b
<img src="./megakiqu.jpg" alt="megakiqu-120B" width="390"/>
MegaDolphin-120B나 Venus-120B과 유사하게 passthrough method로 확장된 모델.

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the passthrough merge method.

### Models Merged

The following models were included in the merge:
* [maywell/kiqu-70b](https://huggingface.co/maywell/kiqu-70b)

## Original Model Card
# **kiqu-70b** [(Arena Leaderboard)](https://huggingface.co/spaces/instructkr/ko-chatbot-arena-leaderboard)


**kiqu-70b** is a SFT+DPO trained model based on Miqu-70B-Alpaca-DPO using **Korean** datasets.

Since this model is finetune of miqu-1-70b using it on commercial purposes is at your own risk. — leaked early version Mistral-Medium

본 모델 **kiqu-70b**는 Miqu-70B-Alpaca-DPO 모델을 기반으로 **한국어** 데이터셋을 사용하여 SFT+DPO 훈련을 진행하여 제작되었습니다.

베이스 모델인 miqu-1-70b 모델이 미스트랄-미디움의 초기 유출 버전이기에 상업적 사용에 대한 risk는 본인에게 있습니다.

Beside that this model follows **cc-by-sa-4.0**

본 모델 자체로서는 **cc-by-sa-4.0**을 따릅니다.

# **Model Details**

**Base Model**  
miqu-1-70b (Early Mistral-Medium)

**Instruction format**

It follows **Mistral** format.
Giving few-shots to model is highly recommended

본 모델은 미스트랄 포맷을 따릅니다.
few-shot 사용을 적극 권장합니다.
```
[INST] {instruction}
[/INST] {output}
```

Multi-shot
```
[INST] {instruction}
[/INST] {output}
[INST] {instruction}
[/INST] {output}
[INST] {instruction}
[/INST] {output}
.
.
.
```

**Recommended Template** - 1-shot with system prompt
```
너는 kiqu-70B라는 한국어에 특화된 언어모델이야. 깔끔하고 자연스럽게 대답해줘!
[INST] 안녕?
[/INST] 안녕하세요! 무엇을 도와드릴까요? 질문이나 궁금한 점이 있다면 언제든지 말씀해주세요.
[INST] {instruction}
[/INST]
```

Trailing space after [/INST] can affect models performance in significant margin. So, when doing inference it is recommended to not include trailing space in chat template.

[/INST] 뒤에 띄어쓰기는 모델 성능에 유의미한 영향을 미칩니다. 따라서, 인퍼런스(추론)과정에서는 챗 템플릿에 띄어쓰기를 제외하는 것을 적극 권장합니다.

### Configuration

The following mergekit's YAML configuration was used to produce this model:

```yaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 20]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [10, 30]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [20, 40]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [30, 50]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [40, 60]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [50, 70]
    model: maywell/kiqu-70b
- sources:
  - layer_range: [60, 80]
    model: maywell/kiqu-70b
```