diff --git a/figures/parameter_size_overview_en.png b/figures/parameter_size_overview_en.png index 205b482..d76323c 100644 Binary files a/figures/parameter_size_overview_en.png and b/figures/parameter_size_overview_en.png differ diff --git a/figures/parameter_size_overview_ja.png b/figures/parameter_size_overview_ja.png index 5dea264..310a3d8 100644 Binary files a/figures/parameter_size_overview_ja.png and b/figures/parameter_size_overview_ja.png differ diff --git a/figures/scripts/parameter_size_overview_ja.csv b/figures/scripts/parameter_size_overview_ja.csv index 6f4da61..52913a0 100644 --- a/figures/scripts/parameter_size_overview_ja.csv +++ b/figures/scripts/parameter_size_overview_ja.csv @@ -1,71 +1,71 @@ Model,Lab,Parameters(B),Announced,Type,Source(JP) -日本語版 Gemma 2 2B,Google,2,2024/10/3,JP-available-CP,https://developers-jp.googleblog.com/2024/10/gemma-2-for-japan.html -Sarashina2-8x70B,SB Intuitions,465,2024/11/8,JP-available,https://www.sbintuitions.co.jp/news/press/20241108_01/ -Sarashina2-70b,SB Intuitions,70,2024/8/7,JP-available,https://huggingface.co/sbintuitions/sarashina2-70b -Sarashina,SB Intuitions,65,2024/6/14,JP-available,https://www.sbintuitions.co.jp/news/press/20240614_01/ -Takane,Fujitsu,104,2024/9/30,JP-unavailable,https://pr.fujitsu.com/jp/news/2024/09/30.html -Fugaku-LLM,"Titech, Tohoku Univ., Fujitsu, RIKEN, Nagoya Univ., CyberAgent, Kotoba Technologies",13,2024/5/10,JP-available,https://www.fujitsu.com/global/about/resources/news/press-releases/2024/0510-01.html -,Rakuten,7,2024/3/21,JP-available-CP,https://corp.rakuten.co.jp/news/press/2024/0321_01.html -KARAKURI 8x7B Instruct,KARAKURI,46.7,2024/6/20,JP-available-CP,https://karakuri.ai/seminar/news/karakuri-lm-8x7b-instruct-v0-1/ -KARAKURI 8x7B Chat,KARAKURI,46.7,2024/5/20,JP-available-CP,https://karakuri.ai/seminar/news/aws_trainium_moe/ -KARAKURI,KARAKURI,70,2024/1/31,JP-available-CP,https://karakuri.ai/seminar/news/karakuri-lm/ -Gemma 2 Baku 2B,rinna,2,2024/10/3,JP-available-CP,https://rinna.co.jp/news/2024/10/20241003.html -Llama 3 Youko (Instruct),rinna,70,2024/07/25,JP-available-CP,https://rinna.co.jp/news/2024/07/20240725.html -Llama 3 Youko,rinna,8,2024/05/07,JP-available-CP,https://rinna.co.jp/news/2024/05/20240507.html -Nekomata,rinna,14,2023/12/21,JP-available-CP,https://rinna.co.jp/news/2023/12/20231221.html -Youri,rinna,7,2023/10/31,JP-available-CP,https://rinna.co.jp/news/2023/10/20231031.html -Llama 3 Swallow,Swallow Project,70,2024/7/1,JP-available-CP,https://swallow-llm.github.io/llama3-swallow.ja.html -Swallow-MX,Swallow Project,46.7,2024/03/11,JP-available-CP,https://tokyotech-llm.github.io/swallow-mistral -Swallow,Swallow Project,70,2023/12/19,JP-available-CP,https://tokyotech-llm.github.io/blog/swallow-llama +Sarashina2-8x70B,SB Intuitions,465,2024/11/08,JP-available,https://www.sbintuitions.co.jp/news/press/20241108_01/ +日本語版 Gemma 2 2B,Google,2,2024/10/03,JP-available-CP,https://developers-jp.googleblog.com/2024/10/gemma-2-for-japan.html +Gemma 2 Baku 2B,rinna,2,2024/10/03,JP-available-CP,https://rinna.co.jp/news/2024/10/20241003.html +Takane,Fujitsu,104,2024/09/30,JP-unavailable,https://pr.fujitsu.com/jp/news/2024/09/30.html LLM-jp-3 13B,LLMC,13,2024/09/25,JP-available,https://llmc.nii.ac.jp/topics/post-707/ +Llama-3-ELYZA-JP-120B,ELYZA,120,2024/09/19,JP-unavailable,https://prtimes.jp/main/html/rd/p/000000053.000047565.html LLM-jp-3 172B beta1,LLMC,172,2024/09/17,JP-available,https://www.nii.ac.jp/news/release/2024/0917.html -LLM-jp-13B v2.0,LLM-jp,13,2024/04/30,JP-available,https://www.nii.ac.jp/news/release/2024/0430.html -LLM-jp-13B,LLM-jp,13,2023/10/20,JP-available,https://www.nii.ac.jp/news/release/2023/1020.html +Tanuki-8x8B,Matsuo Lab LLM Development Project Team Tanuki,47,2024/08/30,JP-available,https://weblab.t.u-tokyo.ac.jp/2024-08-30/ +Llama-3-Ricoh-70B-Instruct,RICOH,70,2024/08/21,JP-unavailable,https://jp.ricoh.com/release/2024/0821_1 +PolySphere-2,AI inside,47.3,2024/08/20,JP-unavailable,https://inside.ai/news/2024/08/20/customizeslm/ +Sarashina2-70b,SB Intuitions,70,2024/08/07,JP-available,https://huggingface.co/sbintuitions/sarashina2-70b +Llama 3 Youko (Instruct),rinna,70,2024/07/25,JP-available-CP,https://rinna.co.jp/news/2024/07/20240725.html +Llama 3 Swallow,Swallow Project,70,2024/07/01,JP-available-CP,https://swallow-llm.github.io/llama3-swallow.ja.html +CALM3,CyberAgent,22,2024/07/01,JP-available,https://huggingface.co/cyberagent/calm3-22b-chat +Llama 3 ELYZA,ELYZA,70,2024/06/26,JP-unavailable,https://note.com/elyza/n/n360b6084fdbd +,ELYZA,8,2024/06/26,JP-available-CP,https://note.com/elyza/n/n360b6084fdbd +KARAKURI 8x7B Instruct,KARAKURI,46.7,2024/06/20,JP-available-CP,https://karakuri.ai/seminar/news/karakuri-lm-8x7b-instruct-v0-1/ +Sarashina,SB Intuitions,65,2024/06/14,JP-available,https://www.sbintuitions.co.jp/news/press/20240614_01/ PLaMo-100B,Preferred Elements,100,2024/06/14,JP-available,"https://tech.preferred.jp/ja/blog/plamo-100b/, https://www.preferred.jp/ja/news/pr20241015/" -PLaMo-13B,Preferred Networks,13,2023/09/28,JP-available,https://www.preferred.jp/ja/news/pr20230928/ +KARAKURI 8x7B Chat,KARAKURI,46.7,2024/05/20,JP-available-CP,https://karakuri.ai/seminar/news/aws_trainium_moe/ Stockmark-100b,Stockmark,100,2024/05/16,JP-available,https://stockmark.co.jp/news/20240516 -Stockmark-13b,Stockmark,13,2023/10/27,JP-available,https://stockmark.co.jp/news/20231027 -Tanuki-8x8B,Matsuo Lab LLM Development Project Team Tanuki,47,2024/08/30,JP-available,https://weblab.t.u-tokyo.ac.jp/2024-08-30/ -Weblab-10B,Matsuo Lab,10,2023/08/22,JP-available,https://www.t.u-tokyo.ac.jp/press/pr2023-08-18-001 -Llama-3-ELYZA-JP-120B,ELYZA,120,2024/09/19,JP-unavailable,https://prtimes.jp/main/html/rd/p/000000053.000047565.html -Llama 3 ELYZA,ELYZA,70,2024/6/26,JP-unavailable,https://note.com/elyza/n/n360b6084fdbd -,ELYZA,8,2024/6/26,JP-available-CP,https://note.com/elyza/n/n360b6084fdbd +Fugaku-LLM,"Titech, Tohoku Univ., Fujitsu, RIKEN, Nagoya Univ., CyberAgent, Kotoba Technologies",13,2024/05/10,JP-available,https://www.fujitsu.com/global/about/resources/news/press-releases/2024/0510-01.html +Japanese Stable LM 2 1.6B,Stability AI,1.6,2024/05/09,JP-available-CP,https://ja.stability.ai/blog/japanese-stable-lm-2-16b +Llama 3 Youko,rinna,8,2024/05/07,JP-available-CP,https://rinna.co.jp/news/2024/05/20240507.html +LLM-jp-13B v2.0,LLM-jp,13,2024/04/30,JP-available,https://www.nii.ac.jp/news/release/2024/0430.html +NIKKEI Language Model,NIKKEI,70,2024/04/24,JP-unavailable,https://www.nikkei.com/article/DGXZQOUC1941R0Z10C24A4000000/ +,ABEJA,46.7,2024/04/20,JP-available-CP,https://tech-blog.abeja.asia/entry/abeja-nedo-project-part1-202404 +,Rakuten,7,2024/03/21,JP-available-CP,https://corp.rakuten.co.jp/news/press/2024/0321_01.html +EvoLLM-JP,Sakana AI,10,2024/03/21,JP-available-CP,https://sakana.ai/evolutionary-model-merge-jp/ ,ELYZA,70,2024/03/12,JP-unavailable,https://elyza.ai/news/2024/03/12/%E3%82%B0%E3%83%AD%E3%83%BC%E3%83%90%E3%83%AB%E3%83%A2%E3%83%87%E3%83%AB%E3%81%AB%E5%8C%B9%E6%95%B5%E3%81%99%E3%82%8B700%E5%84%84%E3%83%91%E3%83%A9%E3%83%A1%E3%83%BC%E3%82%BF%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9Ellm%E3%82%92 +Swallow-MX,Swallow Project,46.7,2024/03/11,JP-available-CP,https://tokyotech-llm.github.io/swallow-mistral +Granite,日本IBM,8,2024/02/27,JP-unavailable,https://jp.newsroom.ibm.com/2024-02-27-IBM-launches-Granite-Japanese-built-on-trusted-data-to-accelerate-Japanese-clients-adoption-of-generative-AI +KARAKURI,KARAKURI,70,2024/01/31,JP-available-CP,https://karakuri.ai/seminar/news/karakuri-lm/ +,RICOH,13,2024/01/31,JP-unavailable,https://jp.ricoh.com/release/2024/0131_1 ,ELYZA,13,2023/12/27,JP-available-CP,https://note.com/elyza/n/n5d42686b60b7 -,ELYZA,7,2023/8/29,JP-available-CP,https://note.com/elyza/n/na405acaca130 -EvoLLM-JP,Sakana AI,10,2024/3/21,JP-available-CP,https://sakana.ai/evolutionary-model-merge-jp/ -Japanese Stable LM 2 1.6B,Stability AI,1.6,2024/05/09,JP-available-CP,https://ja.stability.ai/blog/japanese-stable-lm-2-16b -JSLM Alpha,Stability AI,7,2023/08/10,JP-available,https://ja.stability.ai/blog/japanese-stablelm-alpha +Nekomata,rinna,14,2023/12/21,JP-available-CP,https://rinna.co.jp/news/2023/12/20231221.html +Swallow,Swallow Project,70,2023/12/19,JP-available-CP,https://tokyotech-llm.github.io/blog/swallow-llama JSLM Beta,Stability AI,70,2023/11/02,JP-available-CP,https://ja.stability.ai/blog/japanese-stable-lm-beta -JSLM Gamma,Stability AI,7,2023/10/25,JP-available-CP,https://ja.stability.ai/blog/japanese-stable-lm-3b-4e1tjapanese-stable-lm-gamma-7b -CALM3,CyberAgent,22,2024/7/1,JP-available,https://huggingface.co/cyberagent/calm3-22b-chat CALM2,CyberAgent,7,2023/11/02,JP-available,https://www.cyberagent.co.jp/news/detail/id=29479 -OpenCALM,CyberAgent,6.8,2023/05/17,JP-available,https://www.cyberagent.co.jp/news/detail/id=28817 -,CyberAgent,13,2023/05/11,JP-unavailable,https://www.cyberagent.co.jp/news/detail/id=28797 -,rinna,3.8,2023/07/31,JP-available,https://rinna.co.jp/news/2023/07/20230731.html -,rinna,3.6,2023/05/17,JP-available,https://rinna.co.jp/news/2023/05/20230507.html -,rinna,1.3,2022/01/26,JP-available,https://rinna.co.jp/news/2022/01/2022012601.html -,rinna,0.3,2021/04/07,JP-available,https://rinna.co.jp/news/2021/04/20210407.html -,rinna,0.1,2021/08/25,JP-available,https://rinna.co.jp/news/2021/08/20210825.html -japanese-large-lm,LINE,3.6,2023/08/14,JP-available,https://engineering.linecorp.com/ja/blog/3.6-billion-parameter-japanese-language-model -,レトリバ,3,2023/05/12,JP-available,https://note.com/retrieva/n/n7b4186dc5ada -,ABEJA,46.7,2024/04/20,JP-available-CP,https://tech-blog.abeja.asia/entry/abeja-nedo-project-part1-202404 -,ABEJA,2.7,2022/07/27,JP-available,https://tech-blog.abeja.asia/entry/abeja-gpt-project-202207 -,ABEJA,6.7,2022/07/27,JP-unavailable,https://tech-blog.abeja.asia/entry/abeja-gpt-project-202207 -,ABEJA,13,2022/07/27,JP-unavailable,https://tech-blog.abeja.asia/entry/abeja-gpt-project-202207 -,早大 河原研,1.5,2022/12/15,JP-available,https://zenn.dev/schnell/articles/0eba71dc364b7f -,Yellowback,1.3,2021/12/9,JP-available,https://tech.yellowback.net/posts/gpt-neo-japanese -NIKKEI Language Model,NIKKEI,70,2024/04/24,JP-unavailable,https://www.nikkei.com/article/DGXZQOUC1941R0Z10C24A4000000/ -Granite,日本IBM,8,2024/02/27,JP-unavailable,https://jp.newsroom.ibm.com/2024-02-27-IBM-launches-Granite-Japanese-built-on-trusted-data-to-accelerate-Japanese-clients-adoption-of-generative-AI tsuzumi,NTT,7,2023/11/01,JP-unavailable,https://group.ntt/jp/newsrelease/2023/11/01/231101a.html -,NEC,13,2023/07/06,JP-unavailable,https://jpn.nec.com/press/202307/20230706_02.html +Youri,rinna,7,2023/10/31,JP-available-CP,https://rinna.co.jp/news/2023/10/20231031.html +Stockmark-13b,Stockmark,13,2023/10/27,JP-available,https://stockmark.co.jp/news/20231027 +JSLM Gamma,Stability AI,7,2023/10/25,JP-available-CP,https://ja.stability.ai/blog/japanese-stable-lm-3b-4e1tjapanese-stable-lm-gamma-7b +LLM-jp-13B,LLM-jp,13,2023/10/20,JP-available,https://www.nii.ac.jp/news/release/2023/1020.html ,NICT,179,2023/09/30,JP-unavailable,https://www3.nhk.or.jp/news/html/20231201/k10014275281000.html +PLaMo-13B,Preferred Networks,13,2023/09/28,JP-available,https://www.preferred.jp/ja/news/pr20230928/ +,ELYZA,7,2023/08/29,JP-available-CP,https://note.com/elyza/n/na405acaca130 +Weblab-10B,Matsuo Lab,10,2023/08/22,JP-available,https://www.t.u-tokyo.ac.jp/press/pr2023-08-18-001 +japanese-large-lm,LINE,3.6,2023/08/14,JP-available,https://engineering.linecorp.com/ja/blog/3.6-billion-parameter-japanese-language-model +JSLM Alpha,Stability AI,7,2023/08/10,JP-available,https://ja.stability.ai/blog/japanese-stablelm-alpha +,rinna,3.8,2023/07/31,JP-available,https://rinna.co.jp/news/2023/07/20230731.html +,NEC,13,2023/07/06,JP-unavailable,https://jpn.nec.com/press/202307/20230706_02.html ,NICT,40,2023/07/04,JP-unavailable,https://www.nict.go.jp/press/2023/07/04-1.html -PolySphere-2,AI inside,47.3,2024/08/20,JP-unavailable,https://inside.ai/news/2024/08/20/customizeslm/ PolySphere-1,AI inside,14,2023/06/08,JP-unavailable,https://inside.ai/news/2023/06/08/aiinside-xresearch/ -Llama-3-Ricoh-70B-Instruct,RICOH,70,2024/08/21,JP-unavailable,https://jp.ricoh.com/release/2024/0821_1 -,RICOH,13,2024/1/31,JP-unavailable,https://jp.ricoh.com/release/2024/0131_1 +OpenCALM,CyberAgent,6.8,2023/05/17,JP-available,https://www.cyberagent.co.jp/news/detail/id=28817 +,rinna,3.6,2023/05/17,JP-available,https://rinna.co.jp/news/2023/05/20230507.html +,レトリバ,3,2023/05/12,JP-available,https://note.com/retrieva/n/n7b4186dc5ada +,CyberAgent,13,2023/05/11,JP-unavailable,https://www.cyberagent.co.jp/news/detail/id=28797 ,RICOH,6,2023/03/15,JP-unavailable,https://www.anlp.jp/proceedings/annual_meeting/2023/pdf_dir/H9-4.pdf LHTM-2,オルツ,160,2023/02/14,JP-unavailable,"https://alt.ai/news/news-1892/, https://xtech.nikkei.com/atcl/nxt/column/18/02423/053100030/" +,早大 河原研,1.5,2022/12/15,JP-available,https://zenn.dev/schnell/articles/0eba71dc364b7f HyperCLOVA,NAVER & LIINE,82,2022/11/30,JP-unavailable,https://www.youtube.com/watch?v=I4o7X3-aqJk -HyperCLOVA,NAVER & LIINE,39,2021/11/10,JP-unavailable,https://www.youtube.com/watch?v=V4pZulIWHpY \ No newline at end of file +,ABEJA,2.7,2022/07/27,JP-available,https://tech-blog.abeja.asia/entry/abeja-gpt-project-202207 +,ABEJA,6.7,2022/07/27,JP-unavailable,https://tech-blog.abeja.asia/entry/abeja-gpt-project-202207 +,ABEJA,13,2022/07/27,JP-unavailable,https://tech-blog.abeja.asia/entry/abeja-gpt-project-202207 +,rinna,1.3,2022/01/26,JP-available,https://rinna.co.jp/news/2022/01/2022012601.html +,Yellowback,1.3,2021/12/09,JP-available,https://tech.yellowback.net/posts/gpt-neo-japanese +HyperCLOVA,NAVER & LIINE,39,2021/11/10,JP-unavailable,https://www.youtube.com/watch?v=V4pZulIWHpY +,rinna,0.1,2021/08/25,JP-available,https://rinna.co.jp/news/2021/08/20210825.html +,rinna,0.3,2021/04/07,JP-available,https://rinna.co.jp/news/2021/04/20210407.html \ No newline at end of file