lynx   »   [go: up one dir, main page]

@MichaelBarryUK\n\t check it out -- would like to tag your LI profile:
https://www.linkedin.com/feed/update/urn:li:activity:7188878136430710784?commentUrn=urn%3Ali%3Acomment%3A%28activity%3A7188878136430710784%2C7188905002994671616%29&dashCommentUrn=urn%3Ali%3Afsd_comment%3A%287188905002994671616%2Curn%3Ali%3Aactivity%3A7188878136430710784%29

\n","updatedAt":"2024-04-25T12:31:03.564Z","author":{"_id":"64832a7a7b7195e9d24ef3e9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/2hwAxkt5xFVBhL_ep0Yj-.jpeg","fullname":"Steve Dz","name":"sjdthree","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7818089127540588},"editors":["sjdthree"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/2hwAxkt5xFVBhL_ep0Yj-.jpeg"],"reactions":[],"isReport":false,"parentCommentId":"6628da97b243968a716dc17b"}}]},{"id":"6629182f018354d627164a52","author":{"_id":"65812ce524c030b7d38e4ec5","avatarUrl":"/avatars/0de1c0ed7fab75978c56c4822ad1011b.svg","fullname":"Katastropika","name":"Katastropika","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false},"createdAt":"2024-04-24T14:33:19.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Apple realized their golden age of being considered the king of innovation is long over. Now they're lagging far behind in the generative AI race.","html":"

Apple realized their golden age of being considered the king of innovation is long over. Now they're lagging far behind in the generative AI race.

\n","updatedAt":"2024-04-24T14:33:19.637Z","author":{"_id":"65812ce524c030b7d38e4ec5","avatarUrl":"/avatars/0de1c0ed7fab75978c56c4822ad1011b.svg","fullname":"Katastropika","name":"Katastropika","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9725905060768127},"editors":["Katastropika"],"editorAvatarUrls":["/avatars/0de1c0ed7fab75978c56c4822ad1011b.svg"],"reactions":[{"reaction":"πŸ˜”","users":["julien-c","vedantasp"],"count":2}],"isReport":false}},{"id":"66293e77d0c0b4d7dfb97014","author":{"_id":"6486638da4cf2081f20c40ec","avatarUrl":"/avatars/0bc16a7447cd71ac18828a678313bd83.svg","fullname":"Mike Young","name":"mikelabs","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12},"createdAt":"2024-04-24T17:16:39.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Got a plain-english rewrite of the paper here if anyone is interested: https://www.aimodels.fyi/papers/arxiv/openelm-efficient-language-model-family-open-source","html":"

Got a plain-english rewrite of the paper here if anyone is interested: https://www.aimodels.fyi/papers/arxiv/openelm-efficient-language-model-family-open-source

\n","updatedAt":"2024-04-24T17:16:39.194Z","author":{"_id":"6486638da4cf2081f20c40ec","avatarUrl":"/avatars/0bc16a7447cd71ac18828a678313bd83.svg","fullname":"Mike Young","name":"mikelabs","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.655436635017395},"editors":["mikelabs"],"editorAvatarUrls":["/avatars/0bc16a7447cd71ac18828a678313bd83.svg"],"reactions":[{"reaction":"😎","users":["mikelabs","julien-c"],"count":2}],"isReport":false},"replies":[{"id":"66295634f2063c1a026c40e8","author":{"_id":"5dd96eb166059660ed1ee413","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/NQtzmrDdbG0H8qkZvRyGk.jpeg","fullname":"Julien Chaumond","name":"julien-c","type":"user","isPro":true,"isHf":true,"isHfAdmin":true,"isMod":false,"followerCount":3569},"createdAt":"2024-04-24T18:57:56.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Cool service @mikelabs!","html":"

Cool service \n\n@mikelabs\n\t!

\n","updatedAt":"2024-04-24T18:57:56.117Z","author":{"_id":"5dd96eb166059660ed1ee413","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/NQtzmrDdbG0H8qkZvRyGk.jpeg","fullname":"Julien Chaumond","name":"julien-c","type":"user","isPro":true,"isHf":true,"isHfAdmin":true,"isMod":false,"followerCount":3569}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.3282427489757538},"editors":["julien-c"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/NQtzmrDdbG0H8qkZvRyGk.jpeg"],"reactions":[{"reaction":"❀️","users":["mikelabs"],"count":1}],"isReport":false,"parentCommentId":"66293e77d0c0b4d7dfb97014"}},{"id":"662958b34a7f50a1c3188497","author":{"_id":"6486638da4cf2081f20c40ec","avatarUrl":"/avatars/0bc16a7447cd71ac18828a678313bd83.svg","fullname":"Mike Young","name":"mikelabs","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12},"createdAt":"2024-04-24T19:08:35.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Thank you - please let me know how I can make it better :)","html":"

Thank you - please let me know how I can make it better :)

\n","updatedAt":"2024-04-24T19:08:35.513Z","author":{"_id":"6486638da4cf2081f20c40ec","avatarUrl":"/avatars/0bc16a7447cd71ac18828a678313bd83.svg","fullname":"Mike Young","name":"mikelabs","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.908182680606842},"editors":["mikelabs"],"editorAvatarUrls":["/avatars/0bc16a7447cd71ac18828a678313bd83.svg"],"reactions":[],"isReport":false,"parentCommentId":"66293e77d0c0b4d7dfb97014"}},{"id":"662968be12e915b05371ac61","author":{"_id":"6486638da4cf2081f20c40ec","avatarUrl":"/avatars/0bc16a7447cd71ac18828a678313bd83.svg","fullname":"Mike Young","name":"mikelabs","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12},"createdAt":"2024-04-24T20:17:02.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Mind if I send you a DM on twitter? Tweeted at you!","html":"

Mind if I send you a DM on twitter? Tweeted at you!

\n","updatedAt":"2024-04-24T20:17:02.144Z","author":{"_id":"6486638da4cf2081f20c40ec","avatarUrl":"/avatars/0bc16a7447cd71ac18828a678313bd83.svg","fullname":"Mike Young","name":"mikelabs","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8845658898353577},"editors":["mikelabs"],"editorAvatarUrls":["/avatars/0bc16a7447cd71ac18828a678313bd83.svg"],"reactions":[],"isReport":false,"parentCommentId":"66293e77d0c0b4d7dfb97014"}},{"id":"662b8b10f688584a0577019c","author":{"_id":"5dd96eb166059660ed1ee413","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/NQtzmrDdbG0H8qkZvRyGk.jpeg","fullname":"Julien Chaumond","name":"julien-c","type":"user","isPro":true,"isHf":true,"isHfAdmin":true,"isMod":false,"followerCount":3569},"createdAt":"2024-04-26T11:08:00.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"ah haven't seen, what's your twitter account?","html":"

ah haven't seen, what's your twitter account?

\n","updatedAt":"2024-04-26T11:08:00.361Z","author":{"_id":"5dd96eb166059660ed1ee413","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/NQtzmrDdbG0H8qkZvRyGk.jpeg","fullname":"Julien Chaumond","name":"julien-c","type":"user","isPro":true,"isHf":true,"isHfAdmin":true,"isMod":false,"followerCount":3569}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9454721808433533},"editors":["julien-c"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/NQtzmrDdbG0H8qkZvRyGk.jpeg"],"reactions":[],"isReport":false,"parentCommentId":"66293e77d0c0b4d7dfb97014"}},{"id":"662b98f255fe93e3cd2a824a","author":{"_id":"6486638da4cf2081f20c40ec","avatarUrl":"/avatars/0bc16a7447cd71ac18828a678313bd83.svg","fullname":"Mike Young","name":"mikelabs","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12},"createdAt":"2024-04-26T12:07:14.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"mikeyoung44","html":"

mikeyoung44

\n","updatedAt":"2024-04-26T12:07:14.186Z","author":{"_id":"6486638da4cf2081f20c40ec","avatarUrl":"/avatars/0bc16a7447cd71ac18828a678313bd83.svg","fullname":"Mike Young","name":"mikelabs","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5974575877189636},"editors":["mikelabs"],"editorAvatarUrls":["/avatars/0bc16a7447cd71ac18828a678313bd83.svg"],"reactions":[],"isReport":false,"parentCommentId":"66293e77d0c0b4d7dfb97014"}},{"id":"662c8f57137b72821624ae40","author":{"_id":"645d39b95ebf379fd6da0065","avatarUrl":"/avatars/3d3c25517b9f79b93ed4b758648594a8.svg","fullname":"Victor Biederbeck","name":"victorbiederbeck","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1},"createdAt":"2024-04-27T05:38:31.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2024-10-20T18:32:03.037Z","author":{"_id":"645d39b95ebf379fd6da0065","avatarUrl":"/avatars/3d3c25517b9f79b93ed4b758648594a8.svg","fullname":"Victor Biederbeck","name":"victorbiederbeck","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[],"parentCommentId":"66293e77d0c0b4d7dfb97014"}}]},{"id":"6629b0f0eb150731dab70441","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":264},"createdAt":"2024-04-25T01:25:04.000Z","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* [Stable LM 2 1.6B Technical Report](https://huggingface.co/papers/2402.17834) (2024)\n* [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://huggingface.co/papers/2403.13372) (2024)\n* [Long-Context Language Modeling with Parallel Context Encoding](https://huggingface.co/papers/2402.16617) (2024)\n* [Jamba: A Hybrid Transformer-Mamba Language Model](https://huggingface.co/papers/2403.19887) (2024)\n* [Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference](https://huggingface.co/papers/2403.09636) (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

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":"2024-04-25T01:25:04.634Z","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":264}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7237399220466614},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}},{"id":"6636b40a4130f99a883bfafa","author":{"_id":"648a210e9da3cc3506961585","avatarUrl":"/avatars/808e9d7ac99837fe79169d0b8d49c366.svg","fullname":"Ajith V Prabhakar","name":"ajithprabhakar","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2},"createdAt":"2024-05-04T22:17:46.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"I have featured this paper on my blog - https://ajithp.com/2024/05/04/openelm-apples-groundbreaking-open-language-model/\n","html":"

I have featured this paper on my blog - https://ajithp.com/2024/05/04/openelm-apples-groundbreaking-open-language-model/

\n","updatedAt":"2024-05-04T22:17:46.911Z","author":{"_id":"648a210e9da3cc3506961585","avatarUrl":"/avatars/808e9d7ac99837fe79169d0b8d49c366.svg","fullname":"Ajith V Prabhakar","name":"ajithprabhakar","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.843852162361145},"editors":["ajithprabhakar"],"editorAvatarUrls":["/avatars/808e9d7ac99837fe79169d0b8d49c366.svg"],"reactions":[],"isReport":false}},{"id":"666566f1a1e73728859e2de0","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":142},"createdAt":"2024-06-09T08:25:21.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"# Unlocking New Levels of Language Modeling with OpenELM! 🧠✨\n\nhttps://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/70SHA3sU9Lew-WyVk_xpM.mp4 \n\n## Links πŸ”—:\nπŸ‘‰ Subscribe: https://www.youtube.com/@Arxflix\nπŸ‘‰ Twitter: https://x.com/arxflix\nπŸ‘‰ LMNT (Partner): https://lmnt.com/\n\n\nBy Arxflix\n![9t4iCUHx_400x400-1.jpg](https://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/v4S5zBurs0ouGNwYj1GEd.jpeg)","html":"

Unlocking New Levels of Language Modeling with OpenELM! 🧠✨

\n

\n\n

Links πŸ”—:

\n

πŸ‘‰ Subscribe: https://www.youtube.com/@Arxflix
πŸ‘‰ Twitter: https://x.com/arxflix
πŸ‘‰ LMNT (Partner): https://lmnt.com/

\n

By Arxflix
\"9t4iCUHx_400x400-1.jpg\"

\n","updatedAt":"2024-06-09T08:25:21.641Z","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":142}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5032675862312317},"editors":["blanchon"],"editorAvatarUrls":["/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg"],"reactions":[{"reaction":"πŸ‘","users":["mchorton"],"count":1}],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2404.14619","authors":[{"_id":"662858d84a0dc08679e8f359","user":{"_id":"64f792652003abb61bf5c1b8","avatarUrl":"/avatars/9721810de3519ece50b059c154baa9ca.svg","isPro":false,"fullname":"Sachin Mehta","user":"sacmehta","type":"user"},"name":"Sachin Mehta","status":"admin_assigned","statusLastChangedAt":"2024-04-24T11:15:46.478Z","hidden":false},{"_id":"662858d84a0dc08679e8f35a","user":{"_id":"65ca91986938a6a81fd80d02","avatarUrl":"/avatars/efac7945ac1df4e8949e77465ef0dcbd.svg","isPro":false,"fullname":"Mohammad Hossein Sekhavat","user":"msekhavat","type":"user"},"name":"Mohammad Hossein Sekhavat","status":"admin_assigned","statusLastChangedAt":"2024-04-24T11:15:53.385Z","hidden":false},{"_id":"662858d84a0dc08679e8f35b","user":{"_id":"5f07d37219cb630495b81306","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1595440980042-5f07d37219cb630495b81306.jpeg","isPro":false,"fullname":"Qingqing Cao","user":"csarron","type":"user"},"name":"Qingqing Cao","status":"claimed_verified","statusLastChangedAt":"2024-04-24T11:11:23.174Z","hidden":false},{"_id":"662858d84a0dc08679e8f35c","user":{"_id":"647a5afc732a0cd866eb512f","avatarUrl":"/avatars/fbd0ba2a7ba70414ac903e583ce62933.svg","isPro":false,"fullname":"Maxwell Horton","user":"mchorton","type":"user"},"name":"Maxwell Horton","status":"admin_assigned","statusLastChangedAt":"2024-04-24T10:39:58.055Z","hidden":false},{"_id":"662858d84a0dc08679e8f35d","user":{"_id":"6627307fa39494ebb3a39194","avatarUrl":"/avatars/99290642fd6d4a6162f52cfe5d46c648.svg","isPro":false,"fullname":"Yanzi Jin","user":"yjin25","type":"user"},"name":"Yanzi Jin","status":"admin_assigned","statusLastChangedAt":"2024-04-24T11:15:59.745Z","hidden":false},{"_id":"662858d84a0dc08679e8f35e","user":{"_id":"658895a1c4b20046639a7e59","avatarUrl":"/avatars/f80c3f58efa5d22464590bee7a6041a4.svg","isPro":false,"fullname":"Chenfan Sun","user":"erpang007","type":"user"},"name":"Chenfan Sun","status":"claimed_verified","statusLastChangedAt":"2024-10-17T11:30:02.341Z","hidden":false},{"_id":"662858d84a0dc08679e8f35f","user":{"_id":"66280a4c7c988f33b795f90f","avatarUrl":"/avatars/7a618b39c4ed20f5490ea64fbb67b5ac.svg","isPro":false,"fullname":"Iman Mirzadeh","user":"imirzadeh-apple","type":"user"},"name":"Iman Mirzadeh","status":"admin_assigned","statusLastChangedAt":"2024-04-24T11:16:15.272Z","hidden":false},{"_id":"662858d84a0dc08679e8f360","user":{"_id":"661d992d69a65c0fb0717013","avatarUrl":"/avatars/9d1f20baff742de90a50232db54d2407.svg","isPro":false,"fullname":"Mahyar Najibi","user":"mahyar-najibi","type":"user"},"name":"Mahyar Najibi","status":"admin_assigned","statusLastChangedAt":"2024-04-24T11:16:33.449Z","hidden":false},{"_id":"662858d84a0dc08679e8f361","user":{"_id":"63185e1a70b013d6609416ba","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63185e1a70b013d6609416ba/LOB6bJ71wwgamgN3MCuFb.jpeg","isPro":false,"fullname":"Dmitry Belenko","user":"depthwise","type":"user"},"name":"Dmitry Belenko","status":"claimed_verified","statusLastChangedAt":"2024-04-24T11:11:25.057Z","hidden":false},{"_id":"662858d84a0dc08679e8f362","name":"Peter Zatloukal","hidden":false},{"_id":"662858d84a0dc08679e8f363","user":{"_id":"65d4c7734c2163d05eab4110","avatarUrl":"/avatars/b116a9aca7b0a2a4836a29cb4f069d42.svg","isPro":false,"fullname":"Mohammad Rastegari","user":"mrastegari","type":"user"},"name":"Mohammad Rastegari","status":"admin_assigned","statusLastChangedAt":"2024-04-24T11:16:48.273Z","hidden":false}],"publishedAt":"2024-04-22T23:12:03.000Z","submittedOnDailyAt":"2024-04-24T00:14:11.567Z","title":"OpenELM: An Efficient Language Model Family with Open-source Training\n and Inference Framework","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"The reproducibility and transparency of large language models are crucial for\nadvancing open research, ensuring the trustworthiness of results, and enabling\ninvestigations into data and model biases, as well as potential risks. To this\nend, we release OpenELM, a state-of-the-art open language model. OpenELM uses a\nlayer-wise scaling strategy to efficiently allocate parameters within each\nlayer of the transformer model, leading to enhanced accuracy. For example, with\na parameter budget of approximately one billion parameters, OpenELM exhibits a\n2.36% improvement in accuracy compared to OLMo while requiring 2times fewer\npre-training tokens.\n Diverging from prior practices that only provide model weights and inference\ncode, and pre-train on private datasets, our release includes the complete\nframework for training and evaluation of the language model on publicly\navailable datasets, including training logs, multiple checkpoints, and\npre-training configurations. We also release code to convert models to MLX\nlibrary for inference and fine-tuning on Apple devices. This comprehensive\nrelease aims to empower and strengthen the open research community, paving the\nway for future open research endeavors.\n Our source code along with pre-trained model weights and training recipes is\navailable at https://github.com/apple/corenet. Additionally, \\model\nmodels can be found on HuggingFace at:\nhttps://huggingface.co/apple/OpenELM.","upvotes":126,"discussionId":"662858d84a0dc08679e8f380","ai_summary":"OpenELM, an open language model, uses layer-wise scaling to enhance accuracy and is released with comprehensive training and evaluation frameworks, enabling transparent and reproducible research.","ai_keywords":["layer-wise scaling","transformer model","OpenELM","OLMo","pre-training tokens","training logs","checkpoints","pre-training configurations","MLX library"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63185e1a70b013d6609416ba","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63185e1a70b013d6609416ba/LOB6bJ71wwgamgN3MCuFb.jpeg","isPro":false,"fullname":"Dmitry Belenko","user":"depthwise","type":"user"},{"_id":"655ac762cb17ec19ef82719b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/655ac762cb17ec19ef82719b/1kDncYrGLYS_2SR8cNdAL.png","isPro":false,"fullname":"Welcome to matlok","user":"matlok","type":"user"},{"_id":"629ba6dab406bbde07eb3aae","avatarUrl":"/avatars/bc2254c52dfe6323e1ec0c1ef3ee421b.svg","isPro":false,"fullname":"no","user":"oopslean","type":"user"},{"_id":"5ea4f7a7ba91ce67ad45a95e","avatarUrl":"/avatars/93703e565323afcd226a76cf6baeb0f7.svg","isPro":false,"fullname":"Nick Doiron","user":"monsoon-nlp","type":"user"},{"_id":"65ff6b4f3d247974baba6972","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65ff6b4f3d247974baba6972/-EPxFSSIWNikdakI750az.jpeg","isPro":false,"fullname":"Vinh Nguyen","user":"vinhnx90","type":"user"},{"_id":"6422abd6be23df15743b5ec5","avatarUrl":"/avatars/589e51eba422d3a15bd96298d92ca691.svg","isPro":false,"fullname":"Le Huy Hoang","user":"splendor1811","type":"user"},{"_id":"602707ab4d503386b8e75639","avatarUrl":"/avatars/1195df9636bb4232ec7ff2a13d94ba9e.svg","isPro":false,"fullname":"Mohammad H Sekhavat","user":"mhsekhavat","type":"user"},{"_id":"64747f7e33192631bacd8831","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64747f7e33192631bacd8831/dstkZJ4sHJSeqLesV5cOC.jpeg","isPro":false,"fullname":"Taufiq Dwi Purnomo","user":"taufiqdp","type":"user"},{"_id":"65d4c7734c2163d05eab4110","avatarUrl":"/avatars/b116a9aca7b0a2a4836a29cb4f069d42.svg","isPro":false,"fullname":"Mohammad Rastegari","user":"mrastegari","type":"user"},{"_id":"631ec5fab9a0b2ff1cc183e3","avatarUrl":"/avatars/bd6491632b741746e4a628ff150c55c4.svg","isPro":false,"fullname":"Ivan Parfenchuk","user":"gazebushka","type":"user"},{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"},{"_id":"62a4ac6fd83c3facafa50892","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62a4ac6fd83c3facafa50892/qFpobw9B5XaLZvwn0XbmB.jpeg","isPro":false,"fullname":"Mohammed BrΔ±man","user":"mohammedbriman","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":1}">
Papers
arxiv:2404.14619

OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework

Published on Apr 22, 2024
Β· Submitted by AK on Apr 24, 2024
#1 Paper of the day

Abstract

OpenELM, an open language model, uses layer-wise scaling to enhance accuracy and is released with comprehensive training and evaluation frameworks, enabling transparent and reproducible research.

AI-generated summary

The reproducibility and transparency of large language models are crucial for advancing open research, ensuring the trustworthiness of results, and enabling investigations into data and model biases, as well as potential risks. To this end, we release OpenELM, a state-of-the-art open language model. OpenELM uses a layer-wise scaling strategy to efficiently allocate parameters within each layer of the transformer model, leading to enhanced accuracy. For example, with a parameter budget of approximately one billion parameters, OpenELM exhibits a 2.36% improvement in accuracy compared to OLMo while requiring 2times fewer pre-training tokens. Diverging from prior practices that only provide model weights and inference code, and pre-train on private datasets, our release includes the complete framework for training and evaluation of the language model on publicly available datasets, including training logs, multiple checkpoints, and pre-training configurations. We also release code to convert models to MLX library for inference and fine-tuning on Apple devices. This comprehensive release aims to empower and strengthen the open research community, paving the way for future open research endeavors. Our source code along with pre-trained model weights and training recipes is available at https://github.com/apple/corenet. Additionally, \model models can be found on HuggingFace at: https://huggingface.co/apple/OpenELM.

Community

Great to see developments in the small language model family.

β€œI sense a great disturbance in the source, as if millions of developers suddenly cried out in excitement and were suddenly empowered. I fear something remarkable has happened. The β€˜Apples’ and β€˜Metas’ of the tech empire have opened their vaults, joining the open-source Resistance. This is the beginning of a new collaboration, a new hope for innovation.” πŸŒŒπŸπŸ’» May the source be with you

Β·

Apple realized their golden age of being considered the king of innovation is long over. Now they're lagging far behind in the generative AI race.

Got a plain-english rewrite of the paper here if anyone is interested: https://www.aimodels.fyi/papers/arxiv/openelm-efficient-language-model-family-open-source

Β·

Cool service @mikelabs !

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Unlocking New Levels of Language Modeling with OpenELM! 🧠✨

Links πŸ”—:

πŸ‘‰ Subscribe: https://www.youtube.com/@Arxflix
πŸ‘‰ Twitter: https://x.com/arxflix
πŸ‘‰ LMNT (Partner): https://lmnt.com/

By Arxflix
9t4iCUHx_400x400-1.jpg

Sign up or log in to comment

Models citing this paper 31

Browse 31 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2404.14619 in a dataset README.md to link it from this page.

Spaces citing this paper 14

Collections including this paper 52

Π›ΡƒΡ‡ΡˆΠΈΠΉ частный хостинг