https://huggingface.co/jinaai/jina-embeddings-v3

\n","updatedAt":"2024-09-17T14:11:33.381Z","author":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","fullname":"AK","name":"akhaliq","type":"user","isPro":false,"isHf":true,"isHfAdmin":false,"isMod":false,"followerCount":9179,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.38144469261169434},"editors":["akhaliq"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg"],"reactions":[],"isReport":false}},{"id":"66ea2dbe64583d8d2f4e3c65","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":"2024-09-18T01:32:46.000Z","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* [Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever](https://huggingface.co/papers/2408.16672) (2024)\n* [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://huggingface.co/papers/2407.19669) (2024)\n* [Ruri: Japanese General Text Embeddings](https://huggingface.co/papers/2409.07737) (2024)\n* [NLLB-E5: A Scalable Multilingual Retrieval Model](https://huggingface.co/papers/2409.05401) (2024)\n* [The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design](https://huggingface.co/papers/2408.12503) (2024)\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

\n

\n
• Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever (2024)
\n
• mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval (2024)
\n
• Ruri: Japanese General Text Embeddings (2024)
\n
• NLLB-E5: A Scalable Multilingual Retrieval Model (2024)
\n
• The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design (2024)
\n

\n

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":"2024-09-18T01:32:46.378Z","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":0.7065617442131042},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}},{"id":"674407d6a05eb026d7381b1f","author":{"_id":"64b4f83b966b28317e606037","avatarUrl":"/avatars/e3b1acb4065e833c133c4442260e331c.svg","fullname":"hena","name":"HeNa111","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false},"createdAt":"2024-11-25T05:15:02.000Z","type":"comment","data":{"edited":true,"hidden":false,"latest":{"raw":"\ndoes it support multi-modal","html":"

does it support multi-modal

\n","updatedAt":"2024-11-25T05:16:34.252Z","author":{"_id":"64b4f83b966b28317e606037","avatarUrl":"/avatars/e3b1acb4065e833c133c4442260e331c.svg","fullname":"hena","name":"HeNa111","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.30968737602233887},"editors":["HeNa111"],"editorAvatarUrls":["/avatars/e3b1acb4065e833c133c4442260e331c.svg"],"reactions":[],"isReport":false}},{"id":"674438875809de4a7bfe02b9","author":{"_id":"64c23f6d569648a60737eddb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64c23f6d569648a60737eddb/iZq7bp-yYaGl5VBVoN5Dg.jpeg","fullname":"Saba Sturua","name":"jupyterjazz","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":17,"isUserFollowing":false},"createdAt":"2024-11-25T08:42:47.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"@HeNa111, `jina-embeddings-v3` supports only text. However, we recently released [`jina-clip-v2`](https://huggingface.co/jinaai/jina-clip-v2) which is similar to `jina-embeddings-v3` and additionally supports images.","html":"

\n\n@HeNa111\n\t, jina-embeddings-v3 supports only text. However, we recently released jina-clip-v2 which is similar to jina-embeddings-v3 and additionally supports images.

\n","updatedAt":"2024-11-25T08:42:47.658Z","author":{"_id":"64c23f6d569648a60737eddb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64c23f6d569648a60737eddb/iZq7bp-yYaGl5VBVoN5Dg.jpeg","fullname":"Saba Sturua","name":"jupyterjazz","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":17,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.862115204334259},"editors":["jupyterjazz"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64c23f6d569648a60737eddb/iZq7bp-yYaGl5VBVoN5Dg.jpeg"],"reactions":[],"isReport":false}},{"id":"6759ca251005050c969d6b7e","author":{"_id":"60bfa4237f75bb4d92557db9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60bfa4237f75bb4d92557db9/8Vu3xJkqI59GrtoFrZbwj.jpeg","fullname":"Wilfredo Martel","name":"wilfoderek","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2024-12-11T17:21:41.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Hi everyone!\nI am currently working on a project focused on asymmetric semantic search involving hard negative sentences, and I would like to fine-tune a model using this approach. I am seeking a practical example to better understand the process.\n\nCould you please provide an example , please.\n","html":"

Hi everyone!
I am currently working on a project focused on asymmetric semantic search involving hard negative sentences, and I would like to fine-tune a model using this approach. I am seeking a practical example to better understand the process.

\n

Could you please provide an example , please.

\n","updatedAt":"2024-12-11T17:21:41.714Z","author":{"_id":"60bfa4237f75bb4d92557db9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60bfa4237f75bb4d92557db9/8Vu3xJkqI59GrtoFrZbwj.jpeg","fullname":"Wilfredo Martel","name":"wilfoderek","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9407299160957336},"editors":["wilfoderek"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/60bfa4237f75bb4d92557db9/8Vu3xJkqI59GrtoFrZbwj.jpeg"],"reactions":[],"isReport":false}},{"id":"679761627d631a66940f58a7","author":{"_id":"64d32c8180f189e40bd8e52f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64d32c8180f189e40bd8e52f/wpj9rJZ-vHOvCRkHn4elJ.png","fullname":"Prashant Khairnar","name":"PrashantKhairnar","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false},"createdAt":"2025-01-27T10:35:14.000Z","type":"comment","data":{"edited":true,"hidden":false,"latest":{"raw":"does it work for arabic\n","html":"

does it work for arabic

\n","updatedAt":"2025-01-27T10:35:34.428Z","author":{"_id":"64d32c8180f189e40bd8e52f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64d32c8180f189e40bd8e52f/wpj9rJZ-vHOvCRkHn4elJ.png","fullname":"Prashant Khairnar","name":"PrashantKhairnar","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"fr","probability":0.4394937753677368},"editors":["PrashantKhairnar"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64d32c8180f189e40bd8e52f/wpj9rJZ-vHOvCRkHn4elJ.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2409.10173","authors":[{"_id":"66e926caff154e75c55e597f","user":{"_id":"64c23f6d569648a60737eddb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64c23f6d569648a60737eddb/iZq7bp-yYaGl5VBVoN5Dg.jpeg","isPro":false,"fullname":"Saba Sturua","user":"jupyterjazz","type":"user"},"name":"Saba Sturua","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:08:29.709Z","hidden":false},{"_id":"66e926caff154e75c55e5980","user":{"_id":"64a830cd6cc1a9a131f62619","avatarUrl":"/avatars/0c6ba301a66f2db73049c9fe0e97f2ef.svg","isPro":false,"fullname":"Isabelle Mohr","user":"isacat","type":"user"},"name":"Isabelle Mohr","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:08:44.633Z","hidden":false},{"_id":"66e926caff154e75c55e5981","user":{"_id":"64d22f33032a420d1863b6ea","avatarUrl":"/avatars/ed3eaf4bab70dd6ab9a2b67b5928e4fb.svg","isPro":false,"fullname":"Mohammad Kalim Akram","user":"makram93","type":"user"},"name":"Mohammad Kalim Akram","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:08:51.647Z","hidden":false},{"_id":"66e926caff154e75c55e5982","user":{"_id":"6476ff2699a5ce743ccea3fc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6476ff2699a5ce743ccea3fc/zmFmF8tXXDaAGcl8RYiRr.jpeg","isPro":false,"fullname":"Michael Günther","user":"michael-guenther","type":"user"},"name":"Michael Günther","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:09:15.549Z","hidden":false},{"_id":"66e926caff154e75c55e5983","user":{"_id":"63491dc83d8dc83a55cb749c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63491dc83d8dc83a55cb749c/IoqJrOIaEnYO_S7si4KGp.jpeg","isPro":false,"fullname":"Bo Wang","user":"bwang0911","type":"user"},"name":"Bo Wang","status":"claimed_verified","statusLastChangedAt":"2024-10-02T07:41:34.129Z","hidden":false},{"_id":"66e926caff154e75c55e5984","user":{"_id":"651e707ca92910108b12ecf4","avatarUrl":"/avatars/140ef2d6980aa2d7fec1550d245fc33e.svg","isPro":false,"fullname":"Markus Krimmel","user":"Markus28","type":"user"},"name":"Markus Krimmel","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:10:04.475Z","hidden":false},{"_id":"66e926caff154e75c55e5985","name":"Feng Wang","hidden":false},{"_id":"66e926caff154e75c55e5986","user":{"_id":"64f8620e492828088373ddf9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64f8620e492828088373ddf9/g6XQmUzEPNMQYNc34gYpR.jpeg","isPro":false,"fullname":"Georgios Mastrapas","user":"gmastrapas","type":"user"},"name":"Georgios Mastrapas","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:10:19.566Z","hidden":false},{"_id":"66e926caff154e75c55e5987","user":{"_id":"651e7084570ba4662812114b","avatarUrl":"/avatars/1438e5caa483f63dc0da5ee7508ef7eb.svg","isPro":false,"fullname":"Andreas Koukounas","user":"koukandre","type":"user"},"name":"Andreas Koukounas","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:10:25.511Z","hidden":false},{"_id":"66e926caff154e75c55e5988","user":{"_id":"651e7084570ba4662812114b","avatarUrl":"/avatars/1438e5caa483f63dc0da5ee7508ef7eb.svg","isPro":false,"fullname":"Andreas Koukounas","user":"koukandre","type":"user"},"name":"Andreas Koukounas","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:10:31.608Z","hidden":false},{"_id":"66e926caff154e75c55e5989","user":{"_id":"60124e957bdbda85b0874f7d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60124e957bdbda85b0874f7d/tBxDFq00g3Gz8X0Bv2bwD.jpeg","isPro":false,"fullname":"Nan Wang","user":"nan","type":"user"},"name":"Nan Wang","status":"claimed_verified","statusLastChangedAt":"2024-10-22T08:03:17.814Z","hidden":false},{"_id":"66e926caff154e75c55e598a","user":{"_id":"603763514de52ff951d89793","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/603763514de52ff951d89793/n-QouGYg7oE5QeDaAb3Ns.png","isPro":false,"fullname":"Han Xiao","user":"hanxiao","type":"user"},"name":"Han Xiao","status":"admin_assigned","statusLastChangedAt":"2024-09-17T15:14:54.542Z","hidden":false}],"publishedAt":"2024-09-16T11:10:29.000Z","submittedOnDailyAt":"2024-09-17T12:41:33.374Z","title":"jina-embeddings-v3: Multilingual Embeddings With Task LoRA","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 jina-embeddings-v3, a novel text embedding model with 570\nmillion parameters, achieves state-of-the-art performance on multilingual data\nand long-context retrieval tasks, supporting context lengths of up to 8192\ntokens. The model includes a set of task-specific Low-Rank Adaptation (LoRA)\nadapters to generate high-quality embeddings for query-document retrieval,\nclustering, classification, and text matching. Additionally, Matryoshka\nRepresentation Learning is integrated into the training process, allowing\nflexible truncation of embedding dimensions without compromising performance.\nEvaluation on the MTEB benchmark shows that jina-embeddings-v3 outperforms the\nlatest proprietary embeddings from OpenAI and Cohere on English tasks, while\nachieving superior performance compared to multilingual-e5-large-instruct\nacross all multilingual tasks.","upvotes":33,"discussionId":"66e926cbff154e75c55e59a7","ai_summary":"jina-embeddings-v3, a large-scale text embedding model, achieves state-of-the-art performance in multilingual and long-context retrieval tasks using Low-Rank Adaptation and Matryoshka Representation Learning.","ai_keywords":["Low-Rank Adaptation","LoRA adapters","Matryoshka Representation Learning","MTEB benchmark"],"organization":{"_id":"63563e0c2d14fcd7d83743cf","name":"jinaai","fullname":"Jina AI","avatar":"https://cdn-uploads.huggingface.co/production/uploads/603763514de52ff951d89793/wD54VbAHHyHop3uYlJKl4.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63491dc83d8dc83a55cb749c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63491dc83d8dc83a55cb749c/IoqJrOIaEnYO_S7si4KGp.jpeg","isPro":false,"fullname":"Bo Wang","user":"bwang0911","type":"user"},{"_id":"6317233cc92fd6fee317e030","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6317233cc92fd6fee317e030/cJHSvvimr1kqgQfHOjO5n.png","isPro":false,"fullname":"Tom Aarsen","user":"tomaarsen","type":"user"},{"_id":"60107b385ac3e86b3ea4fc34","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1627505688463-60107b385ac3e86b3ea4fc34.jpeg","isPro":true,"fullname":"Daniel van Strien","user":"davanstrien","type":"user"},{"_id":"6444b3135af87c73bbbd7447","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6444b3135af87c73bbbd7447/-WLquJY3E1KZSJbnYUkwD.jpeg","isPro":true,"fullname":"Frank Sommers","user":"fsommers","type":"user"},{"_id":"6425025862ae109cd74187d5","avatarUrl":"/avatars/e4d319ec0d00a5568405bf3b5dda5c5b.svg","isPro":false,"fullname":"Nick Emb","user":"nicoism","type":"user"},{"_id":"64c23f6d569648a60737eddb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64c23f6d569648a60737eddb/iZq7bp-yYaGl5VBVoN5Dg.jpeg","isPro":false,"fullname":"Saba Sturua","user":"jupyterjazz","type":"user"},{"_id":"62acad9bc35bb36ff09073ca","avatarUrl":"/avatars/e5493dd37ddc875192ca3e5e5c3d9ab7.svg","isPro":false,"fullname":"Alireza Farzaneh","user":"AlirezaF138","type":"user"},{"_id":"64ae46a65d48838462093dfd","avatarUrl":"/avatars/f8c8416e4640eb9d13fbb81fdd9f487b.svg","isPro":false,"fullname":"Aditya Sharma","user":"adi751","type":"user"},{"_id":"635efe2b398ff343c4fa209b","avatarUrl":"/avatars/53ebfcab852efd849a848a26dc65751c.svg","isPro":true,"fullname":"elsatch","user":"elsatch","type":"user"},{"_id":"64e8625b21540e1da324b795","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64e8625b21540e1da324b795/pviqKnJoIEJ1zB55Ybj0A.jpeg","isPro":false,"fullname":"sergicalsix","user":"sergicalsix","type":"user"},{"_id":"5f353bb37e58354338621655","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1639773384591-5f353bb37e58354338621655.jpeg","isPro":false,"fullname":"Nicholas Broad","user":"nbroad","type":"user"},{"_id":"64587be872b60ae7a3817858","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64587be872b60ae7a3817858/BbdOOxOCEzWTvEpkWp8MM.png","isPro":false,"fullname":"Minbyul Jeong","user":"Minbyul","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"63563e0c2d14fcd7d83743cf","name":"jinaai","fullname":"Jina AI","avatar":"https://cdn-uploads.huggingface.co/production/uploads/603763514de52ff951d89793/wD54VbAHHyHop3uYlJKl4.png"}}">