|
|
--- |
|
|
license: llama3 |
|
|
language: |
|
|
- en |
|
|
- ja |
|
|
base_model: |
|
|
- elyza/Llama-3-ELYZA-JP-8B |
|
|
- rinna/llama-3-youko-8b-instruct |
|
|
- lightblue/suzume-llama-3-8B-japanese |
|
|
- neoai-inc/Llama-3-neoAI-8B-Chat-v0.1 |
|
|
- AXCXEPT/Llama-3-EZO-8b-Common-it |
|
|
- tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1 |
|
|
- alfredplpl/Llama-3-8B-Instruct-Ja |
|
|
- haqishen/Llama-3-8B-Japanese-Instruct |
|
|
- owner203/japanese-llama-3-8b-instruct-v2 |
|
|
- shisa-ai/shisa-v1-llama3-8b |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
--- |
|
|
# Llama3-ja |
|
|
|
|
|
<details> |
|
|
<summary>English</summary> |
|
|
|
|
|
## Model Details |
|
|
|
|
|
This model is a linear merge of multiple Llama 3 8B models fine-tuned for Japanese language tasks, created using [mergekit](https://github.com/cg123/mergekit). |
|
|
The aim is to create a more robust and versatile Japanese language model that leverages the strengths of each individual model. |
|
|
|
|
|
## Intended Use |
|
|
|
|
|
This model is designed for various Japanese natural language processing tasks, including but not limited to: |
|
|
|
|
|
- Text generation |
|
|
- Conversation and chatbot applications |
|
|
- Text completion |
|
|
- Question answering |
|
|
- Summarization |
|
|
|
|
|
## Limitations |
|
|
|
|
|
While this model combines multiple Japanese-focused Llama 3 models, it may still have limitations: |
|
|
|
|
|
- Performance on specific tasks may vary |
|
|
- The model may inherit biases from its constituent models |
|
|
|
|
|
## Included models |
|
|
|
|
|
By combining these models, we aim to create a more robust and versatile Japanese language model that leverages the strengths of each individual model. |
|
|
|
|
|
- [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B) |
|
|
- [rinna/llama-3-youko-8b-instruct](https://huggingface.co/rinna/llama-3-youko-8b-instruct) |
|
|
- [lightblue/suzume-llama-3-8B-japanese](https://huggingface.co/lightblue/suzume-llama-3-8B-japanese) |
|
|
- [neoai-inc/Llama-3-neoAI-8B-Chat-v0.1](https://huggingface.co/neoai-inc/Llama-3-neoAI-8B-Chat-v0.1) |
|
|
- [AXCXEPT/Llama-3-EZO-8b-Common-it](https://huggingface.co/AXCXEPT/Llama-3-EZO-8b-Common-it) |
|
|
- [tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1) |
|
|
- [alfredplpl/Llama-3-8B-Instruct-Ja](https://huggingface.co/alfredplpl/Llama-3-8B-Instruct-Ja) |
|
|
- [haqishen/Llama-3-8B-Japanese-Instruct](https://huggingface.co/haqishen/Llama-3-8B-Japanese-Instruct) |
|
|
- [owner203/japanese-llama-3-8b-instruct-v2](https://huggingface.co/owner203/japanese-llama-3-8b-instruct-v2) |
|
|
- [shisa-ai/shisa-v1-llama3-8b](https://huggingface.co/shisa-ai/shisa-v1-llama3-8b) |
|
|
|
|
|
## Acknowledgements |
|
|
|
|
|
Thank you to the creators and contributors of all the component models for their valuable work in advancing Japanese language AI capabilities. |
|
|
</details> |
|
|
|
|
|
<details> |
|
|
<summary>Japanese</summary> |
|
|
|
|
|
## モデル詳細 |
|
|
|
|
|
このモデルは、複数のLlama 3 8Bモデルの線形マージで、日本語タスクにファインチューニングされたものです。[mergekit](https://github.com/cg123/mergekit)を使用して作成されました。 |
|
|
各個別モデルの強みを活用し、より堅牢かつ多様な日本語言学モデルを作成することを目指しています。 |
|
|
|
|
|
## 目的利用 |
|
|
|
|
|
このモデルは、以下のような日本語自然言語処理タスク向けに設計されていますが、これらに限定されません： |
|
|
|
|
|
- テキスト生成 |
|
|
- 会話やチャットボットアプリケーション |
|
|
- テキスト補完 |
|
|
- 質問応答 |
|
|
- 要約 |
|
|
|
|
|
## 制限事項 |
|
|
|
|
|
このモデルは、複数の日本語フォーカスしたLlama 3モデルの組み合わせですが、それでも制限があります： |
|
|
|
|
|
- 特定のタスクでのパフォーマンスが異なる場合がある |
|
|
- モデルは構成要素から偏見を受け継ぐ可能性あり |
|
|
|
|
|
## 含まれるモデル |
|
|
|
|
|
これらのモデルを組み合わせることで、各個別モデルの強みを活用し、より堅牢かつ多様な日本語言学モデルを作成します。 |
|
|
|
|
|
- [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B) |
|
|
- [rinna/llama-3-youko-8b-instruct](https://huggingface.co/rinna/llama-3-youko-8b-instruct) |
|
|
- [lightblue/suzume-llama-3-8B-japanese](https://huggingface.co/lightblue/suzume-llama-3-8B-japanese) |
|
|
- [neoai-inc/Llama-3-neoAI-8B-Chat-v0.1](https://huggingface.co/neoai-inc/Llama-3-neoAI-8B-Chat-v0.1) |
|
|
- [AXCXEPT/Llama-3-EZO-8b-Common-it](https://huggingface.co/AXCXEPT/Llama-3-EZO-8b-Common-it) |
|
|
- [tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1) |
|
|
- [alfredplpl/Llama-3-8B-Instruct-Ja](https://huggingface.co/alfredplpl/Llama-3-8B-Instruct-Ja) |
|
|
- [haqishen/Llama-3-8B-Japanese-Instruct](https://huggingface.co/haqishen/Llama-3-8B-Japanese-Instruct) |
|
|
- [owner203/japanese-llama-3-8b-instruct-v2](https://huggingface.co/owner203/japanese-llama-3-8b-instruct-v2) |
|
|
- [shisa-ai/shisa-v1-llama3-8b](https://huggingface.co/shisa-ai/shisa-v1-llama3-8b) |
|
|
|
|
|
## 謝辞 |
|
|
|
|
|
すべてのコンポーネントモデルの創作者と貢献者に感謝いたします。彼らの価値ある仕事により、日本語AI能力が進歩しました。 |
|
|
</details> |
|
|
|
