Recent searches

No recent searches

Search options

Only available when logged in.
mstdn.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A general-purpose Mastodon server with a 500 character limit. All languages are welcome.

Administered by:

Server stats:

9.6K
active users

mstdn.social: AboutStatusProfiles directoryPrivacy policyTerms of service

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.1

#PyTorch

5 posts2 participants0 posts today
Leanpub<p>From the Leanpub Blog: Leanpub Course LAUNCH 🚀 The Hundred-Page Language Models Course by Andriy Burkov</p><p><a href="https://leanpub.com/blog/leanpub-course-launch-the-hundred-page-language-models-course-by-andriy-burkov-2" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">leanpub.com/blog/leanpub-cours</span><span class="invisible">e-launch-the-hundred-page-language-models-course-by-andriy-burkov-2</span></a></p><p><a href="https://mastodon.social/tags/books" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>books</span></a> <a href="https://mastodon.social/tags/ebooks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ebooks</span></a> <a href="https://mastodon.social/tags/booklaunch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>booklaunch</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearning</span></a> <a href="https://mastodon.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://mastodon.social/tags/AGI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AGI</span></a> <a href="https://mastodon.social/tags/TechBooks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechBooks</span></a> <a href="https://mastodon.social/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a></p>
Leanpub<p>Leanpub Course LAUNCH 🚀 The Hundred-Page Language Models Course: Hands-on with PyTorch by Andriy Burkov</p><p>Watch here: <a href="https://youtu.be/r2EEBL59tLI" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/r2EEBL59tLI</span><span class="invisible"></span></a></p><p>Course Link: <a href="https://leanpub.com/c/theLMcourse" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">leanpub.com/c/theLMcourse</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/books" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>books</span></a> <a href="https://mastodon.social/tags/ebooks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ebooks</span></a> <a href="https://mastodon.social/tags/booklaunch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>booklaunch</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearning</span></a> <a href="https://mastodon.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://mastodon.social/tags/AGI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AGI</span></a> <a href="https://mastodon.social/tags/TechBooks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechBooks</span></a> <a href="https://mastodon.social/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a></p>
Leanpub<p>From the Leanpub Blog: The Leanpub Podcast 🎙️ Feat. Andriy Burkov, Author of The Hundred-Page Language Models Book and The Hundred-Page Language Models Course </p><p><a href="https://leanpub.com/blog/the-leanpub-podcast-feat-andriy-burkov-author-of-the-hundred-page-language-models-book-and-the-hundred-page-language-models-course" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">leanpub.com/blog/the-leanpub-p</span><span class="invisible">odcast-feat-andriy-burkov-author-of-the-hundred-page-language-models-book-and-the-hundred-page-language-models-course</span></a></p><p>Course Link: <a href="https://leanpub.com/c/theLMcourse" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">leanpub.com/c/theLMcourse</span><span class="invisible"></span></a></p><p>Book Link: <a href="https://leanpub.com/theLMbook" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">leanpub.com/theLMbook</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/books" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>books</span></a> <a href="https://mastodon.social/tags/leanpublishing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>leanpublishing</span></a> <a href="https://mastodon.social/tags/selfpublishing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>selfpublishing</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearning</span></a> <a href="https://mastodon.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://mastodon.social/tags/AGI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AGI</span></a> <a href="https://mastodon.social/tags/TechBooks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechBooks</span></a> <a href="https://mastodon.social/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a> <a href="https://mastodon.social/tags/LeanpubPodcast" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LeanpubPodcast</span></a></p>
Leanpub<p>NEW! A Leanpub Podcast Interview 🎙️ Feat. Andriy Burkov, Author of The Hundred-Page Language Models Book and The Hundred-Page Language Models Course</p><p>Watch here: <a href="https://youtu.be/oeNHnO4E0RU" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/oeNHnO4E0RU</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/books" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>books</span></a> <a href="https://mastodon.social/tags/leanpublishing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>leanpublishing</span></a> <a href="https://mastodon.social/tags/selfpublishing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>selfpublishing</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearning</span></a> <a href="https://mastodon.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://mastodon.social/tags/AGI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AGI</span></a> <a href="https://mastodon.social/tags/TechBooks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechBooks</span></a> <a href="https://mastodon.social/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a> <a href="https://mastodon.social/tags/LeanpubPodcast" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LeanpubPodcast</span></a></p>
Jack Atkinson<p>At 11am BST today I'll be delivering a seminar in Leeds as part of the SciML series for the N8 CIR.</p><p>It will be about our FTorch software for coupling <a href="https://hachyderm.io/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> models to <a href="https://hachyderm.io/tags/Fortran" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Fortran</span></a> <br>codes to facilitate hybrid modelling.</p><p>You can register for the stream here: <a href="https://www.eventbrite.co.uk/e/ftorch-a-library-for-coupling-pytorch-models-to-fortran-tickets-1468959069119" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">eventbrite.co.uk/e/ftorch-a-li</span><span class="invisible">brary-for-coupling-pytorch-models-to-fortran-tickets-1468959069119</span></a> and I'll post the slides later today.</p>
Johnny Graber<p><a href="https://mastodon.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> Friday #287: <a href="https://mastodon.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> With <a href="https://mastodon.social/tags/GPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GPU</span></a> Support - <a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a></p><p><a href="https://pythonfriday.dev/2025/07/287-pytorch-with-gpu-support/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">pythonfriday.dev/2025/07/287-p</span><span class="invisible">ytorch-with-gpu-support/</span></a></p>
:rss: DevelopersIO<p>ECS on EC2でGPUとCPUの簡易ベンチマークを測定してみた<br><a href="https://dev.classmethod.jp/articles/2025-07-10-ecs-on-ec2-gpu-cpu-benchmark/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">dev.classmethod.jp/articles/20</span><span class="invisible">25-07-10-ecs-on-ec2-gpu-cpu-benchmark/</span></a></p><p><a href="https://rss-mstdn.studiofreesia.com/tags/dev_classmethod" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dev_classmethod</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/GPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GPU</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/ECS_on_EC2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ECS_on_EC2</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/Amazon_ECS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Amazon_ECS</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/Amazon_EC2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Amazon_EC2</span></a></p>
Pyrzout :vm:<p>How To Train A New Voice For Piper With Only A Single Phrase <a href="https://hackaday.com/2025/07/09/how-to-train-a-new-voice-for-piper-with-only-a-single-phrase/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2025/07/09/how-to</span><span class="invisible">-train-a-new-voice-for-piper-with-only-a-single-phrase/</span></a> <a href="https://social.skynetcloud.site/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://social.skynetcloud.site/tags/speechsynthesis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechsynthesis</span></a> <a href="https://social.skynetcloud.site/tags/texttospeech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>texttospeech</span></a> <a href="https://social.skynetcloud.site/tags/Chatterbox" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Chatterbox</span></a> <a href="https://social.skynetcloud.site/tags/PiperVoice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PiperVoice</span></a> <a href="https://social.skynetcloud.site/tags/pytorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pytorch</span></a> <a href="https://social.skynetcloud.site/tags/whisper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>whisper</span></a> <a href="https://social.skynetcloud.site/tags/gpu" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gpu</span></a></p>
IT News<p>How To Train A New Voice For Piper With Only A Single Phrase - [Cal Bryant] hacked together a home automation system years ago, which more recent... - <a href="https://hackaday.com/2025/07/09/how-to-train-a-new-voice-for-piper-with-only-a-single-phrase/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2025/07/09/how-to</span><span class="invisible">-train-a-new-voice-for-piper-with-only-a-single-phrase/</span></a> <a href="https://schleuss.online/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>artificialintelligence</span></a> <a href="https://schleuss.online/tags/speechsynthesis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechsynthesis</span></a> <a href="https://schleuss.online/tags/texttospeech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>texttospeech</span></a> <a href="https://schleuss.online/tags/chatterbox" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>chatterbox</span></a> <a href="https://schleuss.online/tags/pipervoice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pipervoice</span></a> <a href="https://schleuss.online/tags/pytorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pytorch</span></a> <a href="https://schleuss.online/tags/whisper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>whisper</span></a> <a href="https://schleuss.online/tags/gpu" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gpu</span></a></p>
Habr<p>Собираем MVP product search: дообучение E5 и веб-сервис для сравнения поисквых выдач</p><p>Что важнее: создать продукт , или доставить его до пользователя ? Оба этапа необходимы. Сегодня обсудим второй . Как нам построить поисковую e-com систему. Покажем, что в слово логистика товара входят сложные задачи не только: перевезти наушники из Китая в Америку , но и настройка поисковой выдачи по запросу. Быстро соберем поисковой MVP-сервис . Дообучим модель E5 на реальных данных от Amazon . Определим метрики качества и сравним BM25 , pretrain E5 и fine-tune E5 . Так же взглянем глазами с отладочной информацией и проанализируем изменения поисковых выдач . И под конец обсудим каких технологий еще не хватает и можно добавить, если возникают соответствующие трудности. Погрузиться в семантический поиск →</p><p><a href="https://habr.com/ru/companies/datafeel/articles/925290/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">habr.com/ru/companies/datafeel</span><span class="invisible">/articles/925290/</span></a></p><p><a href="https://zhub.link/tags/machine_learning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machine_learning</span></a> <a href="https://zhub.link/tags/information_retrieval" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>information_retrieval</span></a> <a href="https://zhub.link/tags/semantic_search" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>semantic_search</span></a> <a href="https://zhub.link/tags/huggingface" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>huggingface</span></a> <a href="https://zhub.link/tags/pytorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pytorch</span></a> <a href="https://zhub.link/tags/nlp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlp</span></a> <a href="https://zhub.link/tags/e5" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>e5</span></a> <a href="https://zhub.link/tags/streamlit" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>streamlit</span></a> <a href="https://zhub.link/tags/mvp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>mvp</span></a> <a href="https://zhub.link/tags/%D0%B4%D0%BE%D0%BE%D0%B1%D1%83%D1%87%D0%B5%D0%BD%D0%B8%D0%B5_%D0%BC%D0%BE%D0%B4%D0%B5%D0%BB%D0%B5%D0%B9" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>дообучение_моделей</span></a></p>
Habr<p>Привет, я Ярослав и хочу рассказать, как производили подсчет объема древесины с помощью Computer Vision</p><p>Отвечу почему мужик с линейкой не подойдет и почему нельзя просто взвесить Камаз до и после погрузки</p><p><a href="https://habr.com/ru/articles/925540/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">habr.com/ru/articles/925540/</span><span class="invisible"></span></a></p><p><a href="https://zhub.link/tags/computervision" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computervision</span></a> <a href="https://zhub.link/tags/%D0%BF%D1%80%D0%BE%D0%B8%D0%B7%D0%B2%D0%BE%D0%B4%D1%81%D1%82%D0%B2%D0%BE" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>производство</span></a> <a href="https://zhub.link/tags/pytorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pytorch</span></a></p>
Habr<p>RecBole — «комбайн» на PyTorch для любых рекомендаций</p><p>Привет, Хабр! Сегодня разберём RecBole — универсальный фреймворк на PyTorch, который отвечает на три насущных вопроса любого ML-инженера рекомендаций: Как быстро обкатать десятки алгоритмов (от классического MF до SASRec и KGAT) на собственном датасете — без сотни скриптов? Как хранить все настройки в одном YAML, а не в трёх сотнях аргументов CLI? Как получить честное сравнение метрик и сразу вынести лучший чекпоинт в прод? Рассмотрим подробнее под катом.</p><p><a href="https://habr.com/ru/companies/otus/articles/924426/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">habr.com/ru/companies/otus/art</span><span class="invisible">icles/924426/</span></a></p><p><a href="https://zhub.link/tags/ml" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ml</span></a> <a href="https://zhub.link/tags/RecBole" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RecBole</span></a> <a href="https://zhub.link/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://zhub.link/tags/%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%82%D0%B5%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>рекомендательные_системы</span></a> <a href="https://zhub.link/tags/recommender_system" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>recommender_system</span></a> <a href="https://zhub.link/tags/%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%82%D0%B5%D0%BB%D1%8C%D0%BD%D1%8B%D0%B9_%D1%84%D1%80%D0%B5%D0%B9%D0%BC%D0%B2%D0%BE%D1%80%D0%BA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>рекомендательный_фреймворк</span></a></p>
:rss: Qiita - 人気の記事<p>🔰PyTorchでニューラルネットワーク基礎 #09 【LSTM・多次元化】<br><a href="https://qiita.com/AzukiImo/items/e04318b6845aa609be8f?utm_campaign=popular_items&amp;utm_medium=feed&amp;utm_source=popular_items" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">qiita.com/AzukiImo/items/e0431</span><span class="invisible">8b6845aa609be8f?utm_campaign=popular_items&amp;utm_medium=feed&amp;utm_source=popular_items</span></a></p><p><a href="https://rss-mstdn.studiofreesia.com/tags/qiita" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>qiita</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/%E5%88%9D%E5%BF%83%E8%80%85" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>初心者</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/%E6%B7%B1%E5%B1%A4%E5%AD%A6%E7%BF%92" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>深層学習</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/LSTM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LSTM</span></a> <a href="https://rss-mstdn.studiofreesia.com/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a></p>
Affirmik<p>Anyone had experience with ai foundry vs building their own LLM for small and specific domains? Im loving foundry but not with using custom datasets defined on the fly and having to host a vm just for a vector search index. I wonder if something like pytorch would be better <a href="https://mastodon.social/tags/softwaredevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>softwaredevelopment</span></a> <a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/askfedi" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>askfedi</span></a> <a href="https://mastodon.social/tags/pytorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pytorch</span></a> <a href="https://mastodon.social/tags/programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>programming</span></a></p>
Habr<p>Я построил Vision Transformer с нуля — и научил его обращать внимание</p><p>В этой статье я не просто объясню, что такое ViT — я покажу вам, как создать эту магию своими руками, шаг за шагом, даже если вы никогда раньше не работали с трансформерами для задач с изображениями.</p><p><a href="https://habr.com/ru/articles/925050/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">habr.com/ru/articles/925050/</span><span class="invisible"></span></a></p><p><a href="https://zhub.link/tags/deep_learning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>deep_learning</span></a> <a href="https://zhub.link/tags/pytorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pytorch</span></a> <a href="https://zhub.link/tags/computer_vision" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computer_vision</span></a> <a href="https://zhub.link/tags/transformers" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>transformers</span></a> <a href="https://zhub.link/tags/implementation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>implementation</span></a></p>
JP Lehr<p>I just published our next <a href="https://mast.hpc.social/tags/LLVM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLVM</span></a> <a href="https://mast.hpc.social/tags/Meetup" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Meetup</span></a> in <a href="https://mast.hpc.social/tags/Darmstadt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Darmstadt</span></a> (Germany) on Wed. 30th July, starting 7pm.<br>We will have Lukas Sommer from <a href="https://mast.hpc.social/tags/Codeplay" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Codeplay</span></a> talk about "Compiling Machine Learning Models with <a href="https://mast.hpc.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> 2.0 and <a href="https://mast.hpc.social/tags/Triton" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Triton</span></a>" </p><p>RSVP at <a href="https://www.meetup.com/llvm-social-darmstadt/events/308590919" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">meetup.com/llvm-social-darmsta</span><span class="invisible">dt/events/308590919</span></a> </p><p><a href="https://mast.hpc.social/tags/Compilers" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Compilers</span></a> <a href="https://mast.hpc.social/tags/Software" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Software</span></a></p>
Ahmet Akkoç<p>👀Looking into the future! 📈 Just wanted to share our patient outcome prediction model which we presented at EULAR 2025.</p><p>We have designed a <a href="https://scholar.social/tags/forecasting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>forecasting</span></a> <a href="https://scholar.social/tags/model" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>model</span></a> that can follow a patient's swollen joint count over time and estimate if their <br>condition will improve or worsen. </p><p>ZiteLab <a href="https://scholar.social/tags/pytorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pytorch</span></a> <a href="https://scholar.social/tags/sktime" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>sktime</span></a> <a href="https://scholar.social/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> <a href="https://scholar.social/tags/personalizedmedicine" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>personalizedmedicine</span></a> <a href="https://scholar.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://scholar.social/tags/ml" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ml</span></a> <a href="https://scholar.social/tags/timeseries" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>timeseries</span></a> <a href="https://scholar.social/tags/rheumatology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rheumatology</span></a></p><p>(1/2)</p>
Hacker News<p>Fault Tolerant Llama training – PyTorch blog</p><p><a href="https://pytorch.org/blog/fault-tolerant-llama-training-with-2000-synthetic-failures-every-15-seconds-and-no-checkpoints-on-crusoe-l40s/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">pytorch.org/blog/fault-toleran</span><span class="invisible">t-llama-training-with-2000-synthetic-failures-every-15-seconds-and-no-checkpoints-on-crusoe-l40s/</span></a></p><p><a href="https://mastodon.social/tags/HackerNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HackerNews</span></a> <a href="https://mastodon.social/tags/Fault" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Fault</span></a> <a href="https://mastodon.social/tags/Tolerant" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tolerant</span></a> <a href="https://mastodon.social/tags/Llama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Llama</span></a> <a href="https://mastodon.social/tags/training" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>training</span></a> <a href="https://mastodon.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://mastodon.social/tags/blog" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>blog</span></a> <a href="https://mastodon.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/training" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>training</span></a></p>
Collabora<p>Object detection &amp; tracking with gst-python-ml, a powerful, pure python <a href="https://floss.social/tags/ML" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ML</span></a> framework that supports a broad range of ML vision and language models &amp; works seamlessly with upstream <a href="https://floss.social/tags/GStreamer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GStreamer</span></a> distributions. <a href="https://www.youtube.com/watch?v=vn7p2hXUlcs" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=vn7p2hXUlc</span><span class="invisible">s</span></a> <a href="https://floss.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> <a href="https://floss.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://floss.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://floss.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a></p>
Collabora<p>Object detection &amp; tracking with gst-python-ml, a powerful, pure python <a href="https://floss.social/tags/ML" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ML</span></a> framework that supports a broad range of ML vision and language models &amp; works seamlessly with upstream <a href="https://floss.social/tags/GStreamer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GStreamer</span></a> distributions. <a href="https://www.youtube.com/watch?v=vn7p2hXUlcs" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=vn7p2hXUlc</span><span class="invisible">s</span></a> <a href="https://floss.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> <a href="https://floss.social/tags/PyTorch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyTorch</span></a> <a href="https://floss.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://floss.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a></p>
TrendingLive feeds
About