add LLM-jp-3 172B beta1

.404-links.yml

@@ -1,6 +1,6 @@
 ignore:
   urls:
-    - https://gitlab.llm-jp.nii.ac.jp/datasets/llm-jp-corpus-v2
+    - https://gitlab.llm-jp.nii.ac.jp/datasets/*
     - https://llm-jp.nii.ac.jp/blog/2024/02/09/v1.1-tuning.html
     - https://alaginrc.nict.go.jp/nict-bert/index.html
     - https://www.anlp.jp/*

.vitepress/config.mts

@@ -74,5 +74,17 @@ export default defineConfig({
       },
       link: '/fr/'
     },
+  },
+  vite: {
+    optimizeDeps: {
+      exclude: [
+        "@nolebase/vitepress-plugin-enhanced-readabilities/client",
+      ],
+    },
+    ssr: {
+      noExternal: [
+        "@nolebase/vitepress-plugin-enhanced-readabilities",
+      ],
+    },
   }
 })

.vitepress/theme/index.css

@@ -0,0 +1,11 @@
+.medium-zoom-overlay {
+  z-index: 20;
+}
+
+.medium-zoom-image {
+  z-index: 21;
+}
+
+.VPSocialLinks.VPNavBarSocialLinks.social-links {
+  margin-right: 0;
+}

.vitepress/theme/index.mts

@@ -0,0 +1,34 @@
+import DefaultTheme from 'vitepress/theme';
+import { h } from 'vue';
+
+import './index.css';
+import {
+  NolebaseEnhancedReadabilitiesMenu,
+  NolebaseEnhancedReadabilitiesScreenMenu,
+} from "@nolebase/vitepress-plugin-enhanced-readabilities/client";
+import "@nolebase/vitepress-plugin-enhanced-readabilities/client/style.css";
+import type { Options as NolebaseReadOptions } from '@nolebase/vitepress-plugin-enhanced-readabilities/client'
+import { InjectionKey as NolebaseReadInjectionKey } from '@nolebase/vitepress-plugin-enhanced-readabilities/client'
+
+export default {
+  extends: DefaultTheme,
+  Layout: () => {
+    return h(DefaultTheme.Layout, null, {
+      "nav-screen-content-after": () => h(NolebaseEnhancedReadabilitiesScreenMenu),
+      "nav-bar-content-after": () => h(NolebaseEnhancedReadabilitiesMenu),
+    });
+  },
+  enhanceApp({ app }) {
+    app.provide(NolebaseReadInjectionKey, {
+      layoutSwitch: {
+        defaultMode: 5,
+        contentLayoutMaxWidth: {
+          defaultMaxWidth: 85
+        },
+        pageLayoutMaxWidth: {
+          defaultMaxWidth: 85
+        }
+      }
+    } as NolebaseReadOptions);
+  }
+};

README.md

@@ -2,7 +2,7 @@
 [ [**English**](./en/) | [**Français**](./fr/) | 日本語 ]
 
 <p align="center">
-  <img src="./figures/parameter_size_overview.png" alt="日本語LLM・海外LLMのパラメータサイズの推移">
+  <img src="./figures/parameter_size_overview_ja.png" alt="日本語LLM・海外LLMのパラメータサイズの推移">
 </p>
 <figcaption style="font-style: italic; font-size: 0.9em; color: #6b7280; text-align: center;">日本語LLM・海外LLMのパラメータ数の推移。日本語モデルの情報は本記事、海外モデルの情報は LifeArchitect.ai の <a href="https://lifearchitect.ai/models-table/" target="_blank" rel="noreferrer">Models table</a> を参照しています（ただし、図のスペース上一部のモデルは省略。また、海外モデルのパラメータ数は推測値を含む）。修正・追加等ありましたらお知らせ下さい。</figcaption>
 
@@ -36,6 +36,7 @@
 
 |    |  アーキテクチャ  |  入出力で扱える<br>トークン数  |  学習テキスト  |  開発元  | ライセンス |
 |:---|:---:|:---:|:---:|:---:|:---:|
+| [LLM-jp-3 172B beta1](https://www.nii.ac.jp/news/release/2024/0917.html) | Llama<br>([**172b**-beta1](https://huggingface.co/llm-jp/llm-jp-3-172b-beta1), [**172b**-beta1-instruct](https://huggingface.co/llm-jp/llm-jp-3-172b-beta1-instruct)) | 4,096 | 事前学習: [llm-jp-corpus-v3](https://gitlab.llm-jp.nii.ac.jp/datasets/llm-jp-corpus-v3)<br>Instruction Tuning: [ichikara-instruction](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/), [answer-carefully](https://liat-aip.sakura.ne.jp/wp/answercarefully-dataset/), Dolly Dataset, OASST1, OASST2, Aya Dataset, 	ichikara-instruction-format, Daring-Anteater, FLAN | LLM研究開発センター (LLMC) | LLM-jp-3 172B beta1 Terms of Use |
 | [Stockmark-100b](https://stockmark.co.jp/news/20240516) | Llama<br>([**100b**](https://huggingface.co/stockmark/stockmark-100b), [**100b**-instruct-v0.1](https://huggingface.co/stockmark/stockmark-100b-instruct-v0.1)) | 4,096 | 事前学習: RedPajama, 日本語 Wikipedia, Japanese mC4, Japanese CommonCrawl, 日本語特許, Stockmark Web Corpus<br>(計 **910B** トークン)<br>Instruction Tuning (LoRA): [ichikara-instruction](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/) | ストックマーク | MIT |
 | [Sarashina2](https://www.sbintuitions.co.jp/news/press/20240614_01/) | Llama<br>([**7b**](https://huggingface.co/sbintuitions/sarashina2-7b), [**13b**](https://huggingface.co/sbintuitions/sarashina2-13b), [**70b**](https://huggingface.co/sbintuitions/sarashina2-70b)) | 7b, 13b: 4,096<br>70b: 8,192 | 事前学習: Japanese Common Crawl, SlimPajama, StarCoder<br>(計 **2.1T** トークン) | SB Intuitions | MIT |
 | [Sarashina1](https://www.sbintuitions.co.jp/news/press/20240614_01/) | GPT-NeoX<br>([**7b**](https://huggingface.co/sbintuitions/sarashina1-7b), [**13b**](https://huggingface.co/sbintuitions/sarashina1-13b), [**65b**](https://huggingface.co/sbintuitions/sarashina1-65b)) | 2,048 | 事前学習: Japanese Common Crawl<br>(計 **1T** トークン) | SB Intuitions | MIT |
@@ -465,9 +466,7 @@
 
 このプロジェクトに貢献してくれているコントリビューターのみなさんです！
 
-<a href="https://github.com/llm-jp/awesome-japanese-llm/graphs/contributors" target="_blank" rel="noreferrer">
-  <img src="./figures/contributors.svg" alt="コントリビューター" />
-</a>
+<img loading="lazy" src="./figures/contributors.svg" alt="コントリビューター" />
 
 <a id="citation"></a>
 ## 引用

en/README.md

@@ -2,7 +2,7 @@
 [ English | [**Français**](../fr/) | [**日本語**](../) ]
 
 <p align="center">
-  <img src="../figures/parameter_size_overview.png" alt="Parameter sizes of Japanese and non-Japanese LLMs over time">
+  <img src="../figures/parameter_size_overview_en.png" alt="Parameter sizes of Japanese and non-Japanese LLMs over time">
 </p>
 <figcaption style="font-style: italic; font-size: 0.9em; color: #6b7280; text-align: center;">Evolution of parameter sizes for Japanese LLMs and non-Japanese LLMs. The information on the Japanese models is derived from this article, while the information on the non-Japanese models can be referred from the <a href="https://lifearchitect.ai/models-table/" target="_blank" rel="noreferrer">Models table</a> on LifeArchitect.ai. However, due to space constraints in the figure, some models have been omitted. Additionally, estimates are included in the parameter count for non-Japanese models. Please notify us of any corrections, additions, or updates.</figcaption>
 
@@ -35,6 +35,7 @@ Please point out any errors on the [issues page](https://github.com/llm-jp/aweso
 
 |    |  Architecture  |  Max Context Length  |  Training Data  |  Developer  | License |
 |:---|:---:|:---:|:---:|:---:|:---:|
+| [LLM-jp-3 172B beta1](https://huggingface.co/llm-jp/llm-jp-3-172b-beta1) | Llama<br>([**172b**-beta1](https://huggingface.co/llm-jp/llm-jp-3-172b-beta1), [**172b**-beta1-instruct](https://huggingface.co/llm-jp/llm-jp-3-172b-beta1-instruct)) | 4,096 | Pre-training: [llm-jp-corpus-v3](https://gitlab.llm-jp.nii.ac.jp/datasets/llm-jp-corpus-v3)<br>Instruction Tuning: [ichikara-instruction](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/), [answer-carefully](https://liat-aip.sakura.ne.jp/wp/answercarefully-dataset/), Dolly Dataset, OASST1, OASST2, Aya Dataset, 	ichikara-instruction-format, Daring-Anteater, FLAN | Research and Development Center for Large Language Models (LLMC) | LLM-jp-3 172B beta1 Terms of Use |
 | [Stockmark-100b](https://huggingface.co/stockmark/stockmark-100b) | Llama<br>([**100b**](https://huggingface.co/stockmark/stockmark-100b), [**100b**-instruct-v0.1](https://huggingface.co/stockmark/stockmark-100b-instruct-v0.1)) | 4,096 | Pre-training: RedPajama, Japanese Wikipedia, Japanese mC4, Japanese CommonCrawl, Japanese Patent, Stockmark Web Corpus<br>(**910B** tokens)<br>Instruction Tuning (LoRA): [ichikara-instruction](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/) | Stockmark | MIT |
 | [Sarashina2](https://www.sbintuitions.co.jp/news/press/20240614_01/) | Llama<br>([**7b**](https://huggingface.co/sbintuitions/sarashina2-7b), [**13b**](https://huggingface.co/sbintuitions/sarashina2-13b), [**70b**](https://huggingface.co/sbintuitions/sarashina2-70b)) | 7b, 13b: 4,096<br>70b: 8,192 | Pre-training: Japanese Common Crawl, SlimPajama, StarCoder<br>(**2.1T** tokens) | SB Intuitions | MIT |
 | [Sarashina1](https://www.sbintuitions.co.jp/news/press/20240614_01/) | GPT-NeoX<br>([**7b**](https://huggingface.co/sbintuitions/sarashina1-7b), [**13b**](https://huggingface.co/sbintuitions/sarashina1-13b), [**65b**](https://huggingface.co/sbintuitions/sarashina1-65b)) | 2,048 | Pre-training: Japanese Common Crawl<br>(**1T** tokens) | SB Intuitions | MIT |
@@ -463,9 +464,7 @@ Please point out any errors on the [issues page](https://github.com/llm-jp/aweso
 
 We love contributors! Feel free to contribute to this project.
 
-<a href="https://github.com/llm-jp/awesome-japanese-llm/graphs/contributors" target="_blank" rel="noreferrer">
-  <img src="../figures/contributors.svg" alt="contributors" />
-</a>
+<img loading="lazy" src="../figures/contributors.svg" alt="contributors" />
 
 <a id="citation"></a>
 ## Citation