Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456 Paper page - Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open
Generative Large Language Models
@librarian-bot\n\t recommend\n","updatedAt":"2024-01-31T07:11:38.912Z","author":{"_id":"638eb5f949de7ae552dd6211","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638eb5f949de7ae552dd6211/mJkQJGpn9tXV37N2VLFCh.jpeg","fullname":"Derek Thomas","name":"derek-thomas","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":131,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7918877601623535},"editors":["derek-thomas"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/638eb5f949de7ae552dd6211/mJkQJGpn9tXV37N2VLFCh.jpeg"],"reactions":[{"reaction":"โค๏ธ","users":["davanstrien"],"count":1}],"isReport":false}},{"id":"65b9f2b9504b3aacd1051764","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2024-01-31T07:11:53.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [PersianMind: A Cross-Lingual Persian-English Large Language Model](https://huggingface.co/papers/2401.06466) (2024)\n* [Orion-14B: Open-source Multilingual Large Language Models](https://huggingface.co/papers/2401.12246) (2024)\n* [TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation](https://huggingface.co/papers/2401.14373) (2024)\n* [On the importance of Data Scale in Pretraining Arabic Language Models](https://huggingface.co/papers/2401.07760) (2024)\n* [Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?](https://huggingface.co/papers/2312.12683) (2023)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\n
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
\n
If you want recommendations for any Paper on Hugging Face checkout this Space
\n
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
\n","updatedAt":"2024-01-31T07:11:53.162Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7338705658912659},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2308.16149","authors":[{"_id":"64f0080606fd497b26170eca","user":{"_id":"6429100588215cee63b9334e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6429100588215cee63b9334e/L5-CPVDsIC_1mI_izizyX.jpeg","isPro":false,"fullname":"Neha Sengupta","user":"neha1710","type":"user"},"name":"Neha Sengupta","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:18:23.924Z","hidden":false},{"_id":"64f0080606fd497b26170ecb","user":{"_id":"6172c8ea51681de8a2623df2","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6172c8ea51681de8a2623df2/utzkBPCwoS4jIAHL-5m_z.jpeg","isPro":false,"fullname":"Sunil Kumar Sahu","user":"sunilitggu","type":"user"},"name":"Sunil Kumar Sahu","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:19:30.906Z","hidden":false},{"_id":"64f0080606fd497b26170ecc","name":"Bokang Jia","hidden":false},{"_id":"64f0080606fd497b26170ecd","user":{"_id":"62d00768c375d0c842518541","avatarUrl":"/avatars/2e01b90e4b5c312953ed0a883e336f00.svg","isPro":false,"fullname":"Satheesh K","user":"satheeshkatipomu","type":"user"},"name":"Satheesh Katipomu","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:20:29.321Z","hidden":false},{"_id":"64f0080606fd497b26170ece","user":{"_id":"643934ecb9ac1d55f41cefd7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/643934ecb9ac1d55f41cefd7/v41FZ2Ar6nVXEkf-w5axf.jpeg","isPro":false,"fullname":"Haonan Li","user":"lmlmcat","type":"user"},"name":"Haonan Li","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:20:50.483Z","hidden":false},{"_id":"64f0080606fd497b26170ecf","user":{"_id":"643fb246c2ec31af16aa9313","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/643fb246c2ec31af16aa9313/zCDYOVGdIrncX-k9o7bM6.png","isPro":false,"fullname":"Fajri Koto","user":"fajrikoto","type":"user"},"name":"Fajri Koto","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:21:05.872Z","hidden":false},{"_id":"64f0080606fd497b26170ed0","user":{"_id":"62637f3863f73be3d2f9da5b","avatarUrl":"/avatars/046c7096cf88f50f34516e7da1b18a0a.svg","isPro":false,"fullname":"Osama Mohammed Afzal","user":"oafzal","type":"user"},"name":"Osama Mohammed Afzal","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:21:35.358Z","hidden":false},{"_id":"64f0080606fd497b26170ed1","user":{"_id":"64784adc5bf35e70ab5b747a","avatarUrl":"/avatars/9b3b2d12ad3e1959aacfefbb931986dd.svg","isPro":false,"fullname":"samta kamboj","user":"samta-kamboj","type":"user"},"name":"Samta Kamboj","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:21:52.255Z","hidden":false},{"_id":"64f0080606fd497b26170ed2","user":{"_id":"64a6660602e46deb19ad9114","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64a6660602e46deb19ad9114/KT4ScChS9q8YiWzwfPdLq.png","isPro":false,"fullname":"Onkar Pandit","user":"onkarpandit-g42","type":"user"},"name":"Onkar Pandit","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:22:06.899Z","hidden":false},{"_id":"64f0080606fd497b26170ed3","user":{"_id":"62f346c506b6e6f54b482a20","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62f346c506b6e6f54b482a20/_O4wz8GpDlqCv0ZXiIngL.jpeg","isPro":false,"fullname":"Rahul Pal","user":"rahulpal123","type":"user"},"name":"Rahul Pal","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:22:22.619Z","hidden":false},{"_id":"64f0080606fd497b26170ed4","user":{"_id":"640efae206c3b5ca883e5bce","avatarUrl":"/avatars/d911cffeade203fb620f373479a4fd06.svg","isPro":false,"fullname":"LALIT PRADHAN","user":"lalitpradhan","type":"user"},"name":"Lalit Pradhan","status":"claimed_verified","statusLastChangedAt":"2023-09-21T07:25:42.530Z","hidden":false},{"_id":"64f0080606fd497b26170ed5","user":{"_id":"637e8b1b66ee00bcb2468ed0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1669240174964-637e8b1b66ee00bcb2468ed0.jpeg","isPro":false,"fullname":"Zain","user":"zainmujahid","type":"user"},"name":"Zain Muhammad Mujahid","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:23:02.077Z","hidden":false},{"_id":"64f0080606fd497b26170ed6","user":{"_id":"64eddc2f79845a94dd791ebc","avatarUrl":"/avatars/def0dcf448380873fc29de330b03131f.svg","isPro":false,"fullname":"Massa Baali","user":"massabaali","type":"user"},"name":"Massa Baali","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:23:17.189Z","hidden":false},{"_id":"64f0080606fd497b26170ed7","user":{"_id":"61a4dc053205e107691e0d82","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61a4dc053205e107691e0d82/BESoEHlHYXstXudh6dOdT.jpeg","isPro":true,"fullname":"Alham Fikri Aji","user":"afaji","type":"user"},"name":"Alham Fikri Aji","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:23:46.933Z","hidden":false},{"_id":"64f0080606fd497b26170ed8","user":{"_id":"62fbdc67c776fd8821ae3f2d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62fbdc67c776fd8821ae3f2d/cI7iAZOL40RUYluo5ZVTU.png","isPro":false,"fullname":"Zhengzhong Liu","user":"hunterhector","type":"user"},"name":"Zhengzhong Liu","status":"admin_assigned","statusLastChangedAt":"2024-11-27T01:29:05.092Z","hidden":false},{"_id":"64f0080606fd497b26170ed9","name":"Andy Hock","hidden":false},{"_id":"64f0080606fd497b26170eda","user":{"_id":"629f97653fa7e9d614e91036","avatarUrl":"/avatars/0d901c34b21e505ff3fee16ea1ee242b.svg","isPro":false,"fullname":"Andrew Feldman","user":"afeldman","type":"user"},"name":"Andrew Feldman","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:24:17.683Z","hidden":false},{"_id":"64f0080606fd497b26170edb","name":"Jonathan Lee","hidden":false},{"_id":"64f0080606fd497b26170edc","name":"Andrew Jackson","hidden":false},{"_id":"64f0080606fd497b26170edd","user":{"_id":"647f7eb25e1bc4753746bf9f","avatarUrl":"/avatars/cc9c6210fdc822d8a106937e747dff41.svg","isPro":false,"fullname":"Preslav Nakov","user":"preslavnakov","type":"user"},"name":"Preslav Nakov","status":"admin_assigned","statusLastChangedAt":"2023-08-31T12:25:08.061Z","hidden":false},{"_id":"64f0080606fd497b26170ede","name":"Timothy Baldwin","hidden":false},{"_id":"64f0080606fd497b26170edf","name":"Eric Xing","hidden":false}],"publishedAt":"2023-08-30T17:07:17.000Z","submittedOnDailyAt":"2023-08-31T01:54:54.973Z","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open\n Generative Large Language Models","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"We introduce Jais and Jais-chat, new state-of-the-art Arabic-centric\nfoundation and instruction-tuned open generative large language models (LLMs).\nThe models are based on the GPT-3 decoder-only architecture and are pretrained\non a mixture of Arabic and English texts, including source code in various\nprogramming languages. With 13 billion parameters, they demonstrate better\nknowledge and reasoning capabilities in Arabic than any existing open Arabic\nand multilingual models by a sizable margin, based on extensive evaluation.\nMoreover, the models are competitive in English compared to English-centric\nopen models of similar size, despite being trained on much less English data.\nWe provide a detailed description of the training, the tuning, the safety\nalignment, and the evaluation of the models. We release two open versions of\nthe model -- the foundation Jais model, and an instruction-tuned Jais-chat\nvariant -- with the aim of promoting research on Arabic LLMs. Available at\nhttps://huggingface.co/inception-mbzuai/jais-13b-chat","upvotes":29,"discussionId":"64f0080606fd497b26170ef5","ai_summary":"Jais and Jais-chat, Arabic-centric LLMs based on the GPT-3 architecture, outperform existing models in Arabic and are competitive in English with fewer resources.","ai_keywords":["GPT-3","decoder-only architecture","large language models","Arabic","multilingual","instruction-tuned","safety alignment","evaluation"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"626237d9bbcbd1c34f1bb231","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/626237d9bbcbd1c34f1bb231/EJrOjvAL-68qMCYdnvOrq.png","isPro":true,"fullname":"Ali El Filali","user":"alielfilali01","type":"user"},{"_id":"651c800eb61dff6c00bdffeb","avatarUrl":"/avatars/930955c9408c0c93b8a009aea8c33ea1.svg","isPro":false,"fullname":"Adjlane Aymen","user":"aymen-adj","type":"user"},{"_id":"64eddc2f79845a94dd791ebc","avatarUrl":"/avatars/def0dcf448380873fc29de330b03131f.svg","isPro":false,"fullname":"Massa Baali","user":"massabaali","type":"user"},{"_id":"640603e2c3ab325efa94bc4a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/640603e2c3ab325efa94bc4a/jBLC7JH2dBAkDHYzFXZmr.jpeg","isPro":false,"fullname":"Mohammed Machrouh","user":"medmac01","type":"user"},{"_id":"5f0988ad19cb630495b8147a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5f0988ad19cb630495b8147a/W9PMu6cURwe_RkwovKjdR.jpeg","isPro":false,"fullname":"Sayantan Das","user":"ucalyptus","type":"user"},{"_id":"633241b9fece0490c3d26112","avatarUrl":"/avatars/342cc375aac439c293513cdd75d26a16.svg","isPro":false,"fullname":"geddan","user":"1nader","type":"user"},{"_id":"63138d5854e6e5d9f0f86f2d","avatarUrl":"/avatars/613778fa255df41b696454e058a22d3e.svg","isPro":false,"fullname":"assfag ags asdg","user":"fsdfsadgsadg","type":"user"},{"_id":"64f01afdf88911dd09f209f4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64f01afdf88911dd09f209f4/TUr0iHi4OwFiFYSQBNv6w.jpeg","isPro":false,"fullname":"Yerraboina madhu ","user":"7989madhu","type":"user"},{"_id":"63d4c8ce13ae45b780792f32","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63d4c8ce13ae45b780792f32/QasegimoxBqfZwDzorukz.png","isPro":false,"fullname":"Ohenenoo","user":"PeepDaSlan9","type":"user"},{"_id":"637e8b1b66ee00bcb2468ed0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1669240174964-637e8b1b66ee00bcb2468ed0.jpeg","isPro":false,"fullname":"Zain","user":"zainmujahid","type":"user"},{"_id":"64b794bf104e7af01c0b2b80","avatarUrl":"/avatars/f6243f3788c26c6476021cc23194d8de.svg","isPro":false,"fullname":"Mortadha Abderrahim","user":"Mortadha","type":"user"},{"_id":"6030cba7d2c57896177ce75e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1632603679543-6030cba7d2c57896177ce75e.png","isPro":false,"fullname":"Mohamed BERRIMI","user":"MohamedBerrimi","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":3}">
Jais and Jais-chat, Arabic-centric LLMs based on the GPT-3 architecture, outperform existing models in Arabic and are competitive in English with fewer resources.
AI-generated summary
We introduce Jais and Jais-chat, new state-of-the-art Arabic-centric
foundation and instruction-tuned open generative large language models (LLMs).
The models are based on the GPT-3decoder-only architecture and are pretrained
on a mixture of Arabic and English texts, including source code in various
programming languages. With 13 billion parameters, they demonstrate better
knowledge and reasoning capabilities in Arabic than any existing open Arabic
and multilingual models by a sizable margin, based on extensive evaluation.
Moreover, the models are competitive in English compared to English-centric
open models of similar size, despite being trained on much less English data.
We provide a detailed description of the training, the tuning, the safety
alignment, and the evaluation of the models. We release two open versions of
the model -- the foundation Jais model, and an instruction-tuned Jais-chat
variant -- with the aim of promoting research on Arabic LLMs. Available at
https://huggingface.co/inception-mbzuai/jais-13b-chat
It's truly impressive to witness the development of multilingual Language Models (LLMs) specific in Arabic. Congratulations to everyone involved in this achievement!