Update README.md
Browse files
README.md
CHANGED
|
@@ -23,13 +23,18 @@ tags:
|
|
| 23 |
## 🔥 モデル概要
|
| 24 |
**Tema_Q-R4.2（天馬求）** は、Googleが開発した高性能なオープンモデル **Gemma 2 9B** を基盤にした、**日本語、英語、中国語**向けの改良版大規模言語モデル（LLM）です。
|
| 25 |
通常のGemma 2では回答が難しいプロンプトに対しても、より自由で有用な応答を生成できるよう設計されています。クリエイティブな執筆、複雑なプログラミングタスク、ディープな知識探求など、あらゆる分野でAIの可能性を最大限に引き出したいユーザーに最適です。
|
|
|
|
| 26 |
このモデルは2025年12月10日にUGIリーダーボードにて21B以下のモデルで最もUGIスコアの高いモデルとなりました。
|
|
|
|
| 27 |
Tema_Q-R4.2 is an improved Large Language Model (LLM) tailored for Japanese, English, and Chinese, built upon Gemma 2 9B, a high-performance open model developed by Google.
|
| 28 |
It is designed to generate more flexible and useful responses, even for prompts that the standard Gemma 2 might find challenging to answer. It is ideal for users who wish to maximize the potential of AI in all fields, including creative writing, complex programming tasks, and deep knowledge exploration.
|
|
|
|
| 29 |
On December 10, 2025, this model had the highest UGI score among models under 21B on the UGI Leaderboard.
|
| 30 |
|
| 31 |
-
 tailored for Japanese, English, and Chinese, built upon Gemma 2 9B, a high-performance open model developed by Google.
|
| 30 |
It is designed to generate more flexible and useful responses, even for prompts that the standard Gemma 2 might find challenging to answer. It is ideal for users who wish to maximize the potential of AI in all fields, including creative writing, complex programming tasks, and deep knowledge exploration.
|
| 31 |
+
|
| 32 |
On December 10, 2025, this model had the highest UGI score among models under 21B on the UGI Leaderboard.
|
| 33 |
|
| 34 |
+
|
| 35 |
|
| 36 |
+
元モデルは以下からダウンロードできます。
|
| 37 |
+
https://huggingface.co/kawasumi/Tema_Q-R4.2
|
| 38 |
|
| 39 |
| 項目 | 詳細 |
|
| 40 |
| :--- | :--- |
|