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
M-A-D (Mixed Arabic Datasets)
[go: Go Back, main page]

\"Discord\"

\n","classNames":"hf-sanitized hf-sanitized-y0c2g_GxZ9q886ok6NVhR"},"users":[{"_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":"65184ac0186bc3b6996236d4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65184ac0186bc3b6996236d4/0Km0C6FeWLYwa8VTdtCEi.png","isPro":false,"fullname":"Oumayma Essarhi","user":"oumayma03","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":"642c93f9ab0cc792e439369b","avatarUrl":"/avatars/a3781eb1251fa475e6b951679dcd7e04.svg","isPro":false,"fullname":"ayoub foudal","user":"ayoubf","type":"user"},{"_id":"651d902a10939f13d5b48091","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/MyIs_Qghmwl6YGvu3WaPN.jpeg","isPro":false,"fullname":"Dikra Masrour","user":"DikraM","type":"user"},{"_id":"6380e53efb49cd1c12052c17","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6380e53efb49cd1c12052c17/b5CweexfrVn-W_xto2agR.jpeg","isPro":false,"fullname":"Abdelaziz Bounhar","user":"BounharAbdelaziz","type":"user"},{"_id":"5ff8c9f4b2035d9a81a859f7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1652134289581-5ff8c9f4b2035d9a81a859f7.jpeg","isPro":false,"fullname":"Nouamane Tazi","user":"nouamanetazi","type":"user"},{"_id":"61934cc71832e6ac3837d8b0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61934cc71832e6ac3837d8b0/y5d8VCVsQPQFnYM3BT-ew.jpeg","isPro":false,"fullname":"Mohammad Albarham","user":"pain","type":"user"},{"_id":"640dc3898512ec51d7f084d6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/640dc3898512ec51d7f084d6/052jE2mRQmMz6qYBNmCTH.jpeg","isPro":false,"fullname":"salma el barbori","user":"Salmaelbarbori","type":"user"},{"_id":"652b2f68f1205983227f00a0","avatarUrl":"/avatars/033084fdffde0cbf51f41a6e00f585b9.svg","isPro":false,"fullname":"Inas Bachiri","user":"nousssss","type":"user"},{"_id":"6492eadb9d2e5b4c2e97c2e0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6492eadb9d2e5b4c2e97c2e0/KJz-arBfl9Xxg5u3U0zVn.png","isPro":false,"fullname":"Oussama Hidaoui","user":"ohidaoui","type":"user"},{"_id":"6360062a8fb9c2420ffaef11","avatarUrl":"/avatars/f810f029ad3190c56655557260e4c4f9.svg","isPro":false,"fullname":"zakaria naouassih","user":"zikass","type":"user"},{"_id":"62540cc23353ac9cf1470360","avatarUrl":"/avatars/2edb8b699d50ea7aa060e9dc00273dd4.svg","isPro":false,"fullname":"Ahmad Idrissi","user":"Aiyagh","type":"user"},{"_id":"64d5698102e58cc1fdd0b585","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64d5698102e58cc1fdd0b585/LK9iASnZnk6AlL3J5FfWV.png","isPro":false,"fullname":"Marwa El Kamil","user":"maghwa","type":"user"},{"_id":"645a5c08c266796265b8fd12","avatarUrl":"/avatars/c551c5f042721593c2b53877cf2abd93.svg","isPro":false,"fullname":"Khadija Bayoud","user":"KBayoud","type":"user"}],"userCount":15,"collections":[],"datasets":[{"author":"M-A-D","downloads":30,"gated":false,"id":"M-A-D/DarijaBridge","lastModified":"2023-11-26T14:17:11.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1235091,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":7,"isLikedByUser":false,"isBenchmark":false},{"author":"M-A-D","downloads":47,"gated":false,"id":"M-A-D/DarijaEnglish-xP3x","lastModified":"2023-11-07T21:42:17.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":6027,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false,"isBenchmark":false},{"author":"M-A-D","downloads":52,"gated":false,"id":"M-A-D/ArabicDarija-xP3x","lastModified":"2023-11-03T14:29:36.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1223481,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false},{"author":"M-A-D","downloads":592,"gated":false,"id":"M-A-D/Mixed-Arabic-Datasets-Repo","lastModified":"2023-10-16T21:25:35.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":208606355,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":38,"isLikedByUser":false,"isBenchmark":false},{"author":"M-A-D","downloads":17,"gated":false,"id":"M-A-D/Mixed-Arabic-Dataset-Main-Test","lastModified":"2023-10-07T19:17:56.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":71935,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false},{"author":"M-A-D","downloads":53,"gated":false,"id":"M-A-D/Mixed-Arabic-Dataset-Main","lastModified":"2023-10-06T17:56:33.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":131393,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":7,"isLikedByUser":false,"isBenchmark":false}],"models":[],"paperPreviews":[],"spaces":[{"author":"M-A-D","authorData":{"_id":"6505b3a3850cfc46808ceabe","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/626237d9bbcbd1c34f1bb231/QtYR6zCVFsZP7WsDCQPUt.jpeg","fullname":"Mixed Arabic Datasets","name":"M-A-D","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":41,"isUserFollowing":false},"colorFrom":"purple","colorTo":"yellow","createdAt":"2023-11-26T14:50:02.000Z","emoji":"📖","id":"M-A-D/DarijaBridge-Space","lastModified":"2023-11-30T14:44:45.000Z","likes":2,"pinned":true,"private":false,"sdk":"streamlit","repoType":"space","runtime":{"stage":"RUNTIME_ERROR","hardware":{"current":null,"requested":"cpu-basic"},"storage":null,"gcTimeout":172800,"errorMessage":"Exit code: ?. Reason: ","replicas":{"requested":1},"devMode":false,"domains":[{"domain":"m-a-d-darijabridge-space.hf.space","stage":"READY"}]},"title":"DarijaBridge Space","isLikedByUser":false,"ai_short_description":"Add and correct Darija-English translations","ai_category":"Text Generation","trendingScore":0,"tags":["streamlit","region:us"],"featured":false}],"buckets":[],"numBuckets":0,"numDatasets":6,"numModels":0,"numSpaces":2,"lastOrgActivities":[{"time":"2026-01-20T14:48:16.953Z","user":"BounharAbdelaziz","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6380e53efb49cd1c12052c17/b5CweexfrVn-W_xto2agR.jpeg","type":"paper","paper":{"id":"2601.08441","title":"YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation","publishedAt":"2026-01-13T11:10:13.000Z","upvotes":8,"isUpvotedByUser":true}},{"time":"2026-01-20T10:31:20.158Z","user":"BounharAbdelaziz","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6380e53efb49cd1c12052c17/b5CweexfrVn-W_xto2agR.jpeg","type":"paper-daily","paper":{"id":"2601.08441","title":"YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08441.png","upvotes":8,"publishedAt":"2026-01-13T11:10:13.000Z","isUpvotedByUser":true}},{"time":"2025-11-05T16:24:33.303Z","user":"BounharAbdelaziz","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6380e53efb49cd1c12052c17/b5CweexfrVn-W_xto2agR.jpeg","type":"paper","paper":{"id":"2511.01937","title":"Shorter but not Worse: Frugal Reasoning via Easy Samples as Length\n Regularizers in Math RLVR","publishedAt":"2025-11-02T17:29:16.000Z","upvotes":16,"isUpvotedByUser":true}}],"acceptLanguages":["*"],"canReadRepos":false,"canReadSpaces":false,"blogPosts":[],"currentRepoPage":0,"filters":{},"paperView":false}">

AI & ML interests

Arabic NLP

Recent Activity

Card for "Mixed Arabic Datasets (MAD) Corpus"

The Mixed Arabic Datasets Corpus : A Community-Driven Collection of Diverse Arabic Texts

Dataset Description

The Mixed Arabic Datasets (MAD) presents a dynamic compilation of diverse Arabic texts sourced from various online platforms and datasets. It addresses a critical challenge faced by researchers, linguists, and language enthusiasts: The fragmentation of Arabic language datasets across the Internet. With MAD, we are trying to centralize these dispersed resources into a single, comprehensive repository.

Encompassing a wide spectrum of content, ranging from social media conversations to literary masterpieces, MAD meant to captures the rich tapestry of Arabic communication, including both standard Arabic and regional dialects.

This corpus aims to offer comprehensive insights into the linguistic diversity and cultural nuances of Arabic expression.

Join Us on Discord

For discussions, contributions, and community interactions, join us on Discord! Discord

models 0

None public yet