diff --git a/figures/scripts/parameter_size_overview_generate.py b/figures/scripts/parameter_size_overview_generate.py index ebb8eac..5277179 100644 --- a/figures/scripts/parameter_size_overview_generate.py +++ b/figures/scripts/parameter_size_overview_generate.py @@ -26,8 +26,8 @@ # https://www.jma.go.jp/jma/kishou/info/colorguide/HPColorGuide_202007.pdf LEGEND_COLORS = { # "JP-available-API": "#B40068" - "JP-available": "#FF2800", - "JP-available-CP": "#FF9900", + "JP-available-scratch": "#FF2800", + "JP-available": "#FF9900", "JP-unavailable": "#FFF500", "EN-available": "#0096FF", "EN-unavailable": "#B9EBFF", @@ -35,8 +35,8 @@ legend_labels_ja = { # "JP-available-API": "日本語 (APIとして公開)" - "JP-available": "日本語 (公開, フルスクラッチ学習されたモデル)", - "JP-available-CP": "日本語 (公開)", + "JP-available-scratch": "日本語 (公開, フルスクラッチ学習されたモデル)", + "JP-available": "日本語 (公開)", "JP-unavailable": "日本語 (非公開)", "EN-available": "日本語以外 (公開)", "EN-unavailable": "日本語以外 (非公開)", @@ -44,8 +44,8 @@ legend_labels_en = { # "JP-available-API": "Japanese (public, model weights closed)" - "JP-available": "Japanese (public, built from scratch)", - "JP-available-CP": "Japanese (public)", + "JP-available-scratch": "Japanese (public, built from scratch)", + "JP-available": "Japanese (public)", "JP-unavailable": "Japanese (private)", "EN-available": "non-Japanese (public)", "EN-unavailable": "non-Japanese (private)", @@ -118,20 +118,20 @@ def draw_figure(df: pd.DataFrame, locale: Literal['ja', 'en']): ) ax.scatter( - df[df["Type"] == "JP-available-CP"]["Announced"], - df[df["Type"] == "JP-available-CP"]["Parameters(B)"], - color=LEGEND_COLORS["JP-available-CP"], - label=LEGEND_LABELS[locale]["JP-available-CP"], + df[df["Type"] == "JP-available"]["Announced"], + df[df["Type"] == "JP-available"]["Parameters(B)"], + color=LEGEND_COLORS["JP-available"], + label=LEGEND_LABELS[locale]["JP-available"], s=150, linewidth=0.5, edgecolors="gray" ) ax.scatter( - df[df["Type"] == "JP-available"]["Announced"], - df[df["Type"] == "JP-available"]["Parameters(B)"], - color=LEGEND_COLORS["JP-available"], - label=LEGEND_LABELS[locale]["JP-available"], + df[df["Type"] == "JP-available-scratch"]["Announced"], + df[df["Type"] == "JP-available-scratch"]["Parameters(B)"], + color=LEGEND_COLORS["JP-available-scratch"], + label=LEGEND_LABELS[locale]["JP-available-scratch"], s=150, linewidth=0.5, edgecolors="gray" diff --git a/figures/scripts/parameter_size_overview_ja.csv b/figures/scripts/parameter_size_overview_ja.csv index 52913a0..7d0832b 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) -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 +Sarashina2-8x70B,SB Intuitions,465,2024/11/08,JP-available-scratch,https://www.sbintuitions.co.jp/news/press/20241108_01/ +日本語版 Gemma 2 2B,Google,2,2024/10/03,JP-available,https://developers-jp.googleblog.com/2024/10/gemma-2-for-japan.html +Gemma 2 Baku 2B,rinna,2,2024/10/03,JP-available,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/ +LLM-jp-3 13B,LLMC,13,2024/09/25,JP-available-scratch,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 -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/ +LLM-jp-3 172B beta1,LLMC,172,2024/09/17,JP-available-scratch,https://www.nii.ac.jp/news/release/2024/0917.html +Tanuki-8x8B,Matsuo Lab LLM Development Project Team Tanuki,47,2024/08/30,JP-available-scratch,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 +Sarashina2-70b,SB Intuitions,70,2024/08/07,JP-available-scratch,https://huggingface.co/sbintuitions/sarashina2-70b +Llama 3 Youko (Instruct),rinna,70,2024/07/25,JP-available,https://rinna.co.jp/news/2024/07/20240725.html +Llama 3 Swallow,Swallow Project,70,2024/07/01,JP-available,https://swallow-llm.github.io/llama3-swallow.ja.html +CALM3,CyberAgent,22,2024/07/01,JP-available-scratch,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/" -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 -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 +,ELYZA,8,2024/06/26,JP-available,https://note.com/elyza/n/n360b6084fdbd +KARAKURI 8x7B Instruct,KARAKURI,46.7,2024/06/20,JP-available,https://karakuri.ai/seminar/news/karakuri-lm-8x7b-instruct-v0-1/ +Sarashina,SB Intuitions,65,2024/06/14,JP-available-scratch,https://www.sbintuitions.co.jp/news/press/20240614_01/ +PLaMo-100B,Preferred Elements,100,2024/06/14,JP-available-scratch,"https://tech.preferred.jp/ja/blog/plamo-100b/, https://www.preferred.jp/ja/news/pr20241015/" +KARAKURI 8x7B Chat,KARAKURI,46.7,2024/05/20,JP-available,https://karakuri.ai/seminar/news/aws_trainium_moe/ +Stockmark-100b,Stockmark,100,2024/05/16,JP-available-scratch,https://stockmark.co.jp/news/20240516 +Fugaku-LLM,"Titech, Tohoku Univ., Fujitsu, RIKEN, Nagoya Univ., CyberAgent, Kotoba Technologies",13,2024/05/10,JP-available-scratch,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,https://ja.stability.ai/blog/japanese-stable-lm-2-16b +Llama 3 Youko,rinna,8,2024/05/07,JP-available,https://rinna.co.jp/news/2024/05/20240507.html +LLM-jp-13B v2.0,LLM-jp,13,2024/04/30,JP-available-scratch,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/ +,ABEJA,46.7,2024/04/20,JP-available,https://tech-blog.abeja.asia/entry/abeja-nedo-project-part1-202404 +,Rakuten,7,2024/03/21,JP-available,https://corp.rakuten.co.jp/news/press/2024/0321_01.html +EvoLLM-JP,Sakana AI,10,2024/03/21,JP-available,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 +Swallow-MX,Swallow Project,46.7,2024/03/11,JP-available,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/ +KARAKURI,KARAKURI,70,2024/01/31,JP-available,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 -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 -CALM2,CyberAgent,7,2023/11/02,JP-available,https://www.cyberagent.co.jp/news/detail/id=29479 +,ELYZA,13,2023/12/27,JP-available,https://note.com/elyza/n/n5d42686b60b7 +Nekomata,rinna,14,2023/12/21,JP-available,https://rinna.co.jp/news/2023/12/20231221.html +Swallow,Swallow Project,70,2023/12/19,JP-available,https://tokyotech-llm.github.io/blog/swallow-llama +JSLM Beta,Stability AI,70,2023/11/02,JP-available,https://ja.stability.ai/blog/japanese-stable-lm-beta +CALM2,CyberAgent,7,2023/11/02,JP-available-scratch,https://www.cyberagent.co.jp/news/detail/id=29479 tsuzumi,NTT,7,2023/11/01,JP-unavailable,https://group.ntt/jp/newsrelease/2023/11/01/231101a.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 +Youri,rinna,7,2023/10/31,JP-available,https://rinna.co.jp/news/2023/10/20231031.html +Stockmark-13b,Stockmark,13,2023/10/27,JP-available-scratch,https://stockmark.co.jp/news/20231027 +JSLM Gamma,Stability AI,7,2023/10/25,JP-available,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-scratch,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 +PLaMo-13B,Preferred Networks,13,2023/09/28,JP-available-scratch,https://www.preferred.jp/ja/news/pr20230928/ +,ELYZA,7,2023/08/29,JP-available,https://note.com/elyza/n/na405acaca130 +Weblab-10B,Matsuo Lab,10,2023/08/22,JP-available-scratch,https://www.t.u-tokyo.ac.jp/press/pr2023-08-18-001 +japanese-large-lm,LINE,3.6,2023/08/14,JP-available-scratch,https://engineering.linecorp.com/ja/blog/3.6-billion-parameter-japanese-language-model +JSLM Alpha,Stability AI,7,2023/08/10,JP-available-scratch,https://ja.stability.ai/blog/japanese-stablelm-alpha +,rinna,3.8,2023/07/31,JP-available-scratch,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-1,AI inside,14,2023/06/08,JP-unavailable,https://inside.ai/news/2023/06/08/aiinside-xresearch/ -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 +OpenCALM,CyberAgent,6.8,2023/05/17,JP-available-scratch,https://www.cyberagent.co.jp/news/detail/id=28817 +,rinna,3.6,2023/05/17,JP-available-scratch,https://rinna.co.jp/news/2023/05/20230507.html +,レトリバ,3,2023/05/12,JP-available-scratch,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 +,早大 河原研,1.5,2022/12/15,JP-available-scratch,https://zenn.dev/schnell/articles/0eba71dc364b7f HyperCLOVA,NAVER & LIINE,82,2022/11/30,JP-unavailable,https://www.youtube.com/watch?v=I4o7X3-aqJk -,ABEJA,2.7,2022/07/27,JP-available,https://tech-blog.abeja.asia/entry/abeja-gpt-project-202207 +,ABEJA,2.7,2022/07/27,JP-available-scratch,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 +,rinna,1.3,2022/01/26,JP-available-scratch,https://rinna.co.jp/news/2022/01/2022012601.html +,Yellowback,1.3,2021/12/09,JP-available-scratch,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 +,rinna,0.1,2021/08/25,JP-available-scratch,https://rinna.co.jp/news/2021/08/20210825.html +,rinna,0.3,2021/04/07,JP-available-scratch,https://rinna.co.jp/news/2021/04/20210407.html \ No newline at end of file