Recent searches

No recent searches

Search options

Only available when logged in.
eupolicy.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
This Mastodon server is a friendly and respectful discussion space for people working in areas related to EU policy. When you request to create an account, please tell us something about you.

Administered by:

Server stats:

201
active users

eupolicy.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.1

#ollama

10 posts10 participants0 posts today
🔘 G◍M◍◍T 🔘<p>💡 OpenAI lancia 2 modelli open source gpt-oss: potenza AI alla portata di tutti</p><p><a href="https://gomoot.com/openai-lancia-2-modelli-open-source-gpt-oss-potenza-ai-alla-portata-di-tutti/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">gomoot.com/openai-lancia-2-mod</span><span class="invisible">elli-open-source-gpt-oss-potenza-ai-alla-portata-di-tutti/</span></a></p><p><a href="https://mastodon.uno/tags/apache2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>apache2</span></a> <a href="https://mastodon.uno/tags/blog" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>blog</span></a> <a href="https://mastodon.uno/tags/gpt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gpt</span></a> <a href="https://mastodon.uno/tags/gtposs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gtposs</span></a> <a href="https://mastodon.uno/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a> <a href="https://mastodon.uno/tags/lmstudio" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>lmstudio</span></a> <a href="https://mastodon.uno/tags/news" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>news</span></a> <a href="https://mastodon.uno/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> <a href="https://mastodon.uno/tags/openai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>openai</span></a> <a href="https://mastodon.uno/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> <a href="https://mastodon.uno/tags/picks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>picks</span></a> <a href="https://mastodon.uno/tags/tech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tech</span></a> <a href="https://mastodon.uno/tags/tecnologia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tecnologia</span></a> <a href="https://mastodon.uno/tags/vcode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>vcode</span></a></p>
C++ Wage Slave<p>If you think MP3 sounds good, choose a song you love that has a detailed, spacious sound, and encode it in <a href="https://infosec.space/tags/MP3" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MP3</span></a> at low bandwidth. Hear the jangly tuning, the compression artifacts, the lack of detail and stability and the claustrophobic sound. Now that you know it's there, you'll detect it even in MP3 samples at higher bitrates.</p><p>This toot is actually about <a href="https://infosec.space/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenerativeAI</span></a>. If you can, download <a href="https://infosec.space/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a> and try some small models with no more than, say, 4bn parameters. Ask detailed questions about subjects you understand in depth. Watch the models hallucinate, miss the point, make logical errors and give bad advice. See them get hung up on one specific word and launch off at a tangent. Notice how the tone is always the same, whether they're talking sense or not.</p><p>Once you've seen the problems with small models, you'll spot them even in much larger models. You'll be inoculated against the idea that <a href="https://infosec.space/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a> are intelligent, conscious or trustworthy. That, today, is an important life skill.</p>
EventHub<p>Wir haben spaßeshalber mal ein lokales Large Language Model (LLM) über einen Retrieval Augmented Generation (RAG) -Ansatz mit Veranstaltungen des EventHub gefüttert. </p><p>Rausgekommen, ist ein Chatbot, den man über den Browser nach Veranstaltungen fragen kann.</p><p>Eine Oberfläche wäre leicht zu machen. </p><p>Ich denke jedoch nicht, dass das wirklich jemand braucht. Oder doch?</p><p><a href="https://feedbeat.me/tags/ki" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ki</span></a> <a href="https://feedbeat.me/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://feedbeat.me/tags/chat" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>chat</span></a> <a href="https://feedbeat.me/tags/chatbot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>chatbot</span></a> <a href="https://feedbeat.me/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> <a href="https://feedbeat.me/tags/krefeld" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>krefeld</span></a></p>
Lukas Weidinger<p>Richtig enttäuschend war der Einstieg in Handschrift-<a href="https://gruene.social/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> mit <a href="https://gruene.social/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a>. Deutlich besser war <a href="https://gruene.social/tags/llama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llama</span></a>-vision mit <a href="https://gruene.social/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> auf dem Alpaca-Flatpak. Das Setup hat es allerdings nicht geschafft, meine CPU im Notebook richtig zu nutzen und war entsprechend langsam. Ein <a href="https://gruene.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> mit Bildverarbeitung scheint mir auch Overkill zu sein.</p>
Teodor Gross<p>I invented `.awesome-ai.md` - the new standard for AI tool discovery! </p><p>Like `.gitignore` for Git, but for AI tools on GitHub . My system automatically scans the entire GitHub and discovers new AI projects.</p><p>Website: <a href="https://awesome-ai.io/submit-info" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">awesome-ai.io/submit-info</span><span class="invisible"></span></a><br>Repository: <a href="https://github.com/teodorgross/awesome-ai" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/teodorgross/awesome</span><span class="invisible">-ai</span></a></p><p><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/GitHub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHub</span></a> <a href="https://mastodon.social/tags/Innovation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Innovation</span></a> <a href="https://mastodon.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a> <a href="https://mastodon.social/tags/dev" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dev</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/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> <a href="https://mastodon.social/tags/sysadmin" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>sysadmin</span></a> <a href="https://mastodon.social/tags/linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linux</span></a> <a href="https://mastodon.social/tags/aitools" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aitools</span></a></p>
hgrsd<p>Oh, and I should add that it also supports pointing the tool at any URL that implements an OpenAI (or Anthropic) compatible API, including your local servers. This means that you can use it with Ollama and any model that you expose through it. </p><p><a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://hachyderm.io/tags/rust" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rust</span></a> <a href="https://hachyderm.io/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> <a href="https://hachyderm.io/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a> <a href="https://hachyderm.io/tags/coding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>coding</span></a></p>
Michael Blume<p><span class="h-card" translate="no"><a href="https://chaos.social/@root42" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>root42</span></a></span> </p><p>Ja, früher war alles besser... ;-) </p><p>Ernsthaft: Es gibt auch hier im <a href="https://sueden.social/tags/Fediversum" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Fediversum</span></a> eine sehr aktive Szene, die bereits lokale KI-Anwendungen ausprobieren, beispielsweise via <a href="https://sueden.social/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a>. </p><p><span class="h-card" translate="no"><a href="https://friendica.andreaskilgus.de/profile/musenhain" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>musenhain</span></a></span> </p><p><a href="https://ollama.org/de/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">ollama.org/de/</span><span class="invisible"></span></a></p>
Yann Büchau :nixos:<p><span class="h-card" translate="no"><a href="https://23.social/@alios" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>alios</span></a></span> <span class="h-card" translate="no"><a href="https://muenchen.social/@dyfustic" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>dyfustic</span></a></span> Ich kann mir das nicht anhören, ein Kollege hat mir sowas mal geschickt und mich cringt es absolut zusammen 🥶 Aber sowas wie <a href="https://fosstodon.org/tags/paperless" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paperless</span></a> plus lokales <a href="https://fosstodon.org/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> ohne Google wäre hilfreich.</p>
Markus Eisele<p>Ollama v0.10.0 is here! Major highlights:</p><p>- New native app for macOS &amp; Windows<br>- 2-3x performance boost for Gemma3 models <br>- 10-30% faster multi-GPU performance<br>- Fixed tool calling issues with <a href="https://mastodon.online/tags/Granite3" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Granite3</span></a>.3 &amp; Mistral-Nemo<br>- `ollama ps` now shows context length<br>- WebP image support in OpenAI API</p><p><a href="https://github.com/ollama/ollama/releases/tag/v0.10.0" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/ollama/ollama/relea</span><span class="invisible">ses/tag/v0.10.0</span></a></p><p><a href="https://mastodon.online/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a> <a href="https://mastodon.online/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.online/tags/LocalLLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LocalLLM</span></a> <a href="https://mastodon.online/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a></p>
Denzil Ferreira<p>Ollama's new app · for Mac and Windows... Where's our Linux version? I wonder how well this works with Nvidia and AMD cards on Windowland.</p><p><a href="https://techhub.social/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> <a href="https://techhub.social/tags/app" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>app</span></a></p><p><a href="https://ollama.com/blog/new-app" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">ollama.com/blog/new-app</span><span class="invisible"></span></a></p>
Hirad<p>Ollama has created a graphical application for Windows and macOS, and there is no mention of Linux 🙄</p><p><a href="https://ollama.com/blog/new-app" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">ollama.com/blog/new-app</span><span class="invisible"></span></a></p><p><a href="https://m.hirad.it/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a> <a href="https://m.hirad.it/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://m.hirad.it/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://m.hirad.it/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a></p>
Martin<p>Ich würde mich gern mit Leuten austauschen, die <a href="https://social.cologne/tags/AnythingLLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AnythingLLM</span></a> mit <a href="https://social.cologne/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a> lokal verwenden. <br>Perfekt fände ich eine <a href="https://social.cologne/tags/Threema" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Threema</span></a> Gruppe, um sich auszutauschen und auch mal Schrachnachrichten senden zu können.<br>Hat jemand Interesse?<br>😊</p>
Markus Eisele<p>Building a Real-Time Collaborative AI Editor with Quarkus, CRDTs, and Local LLMs<br>Learn how to combine CRDTs, WebSockets, and a local LLM to build a fast, conflict-free collaborative text editor with AI suggestions <br><a href="https://myfear.substack.com/p/real-time-ai-editor-quarkus-crdt-langchain4j" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">myfear.substack.com/p/real-tim</span><span class="invisible">e-ai-editor-quarkus-crdt-langchain4j</span></a><br><a href="https://mastodon.online/tags/Java" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Java</span></a> <a href="https://mastodon.online/tags/Websockets" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Websockets</span></a> <a href="https://mastodon.online/tags/Quarkus" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Quarkus</span></a> <a href="https://mastodon.online/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.online/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a> <a href="https://mastodon.online/tags/LangChain4j" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LangChain4j</span></a></p>
Simon Dückert<p>Frage an alle <a href="https://colearn.social/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> Nutzer:innen: welche lokalen LLMs nutzt ihr regelmäßig (nicht: welche habt ihr installiert)?</p>
Markus Eisele<p>Fast and Smart: Content Moderation with Java, Bloom Filters, and Local LLMs<br>Build a blazing-fast moderation API in Quarkus that filters content intelligently using n-grams, probabilistic data structures, and llama3.<br><a href="https://myfear.substack.com/p/quarkus-content-moderation-bloom-filter-llm" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">myfear.substack.com/p/quarkus-</span><span class="invisible">content-moderation-bloom-filter-llm</span></a><br><a href="https://mastodon.online/tags/Java" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Java</span></a> <a href="https://mastodon.online/tags/Quarkus" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Quarkus</span></a> <a href="https://mastodon.online/tags/Langchain4j" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Langchain4j</span></a> <a href="https://mastodon.online/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> <a href="https://mastodon.online/tags/BloomFilter" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BloomFilter</span></a></p>
Ivan Todorov<p>Using Home Assistant OS, I wired up Whisper for speech recognition, Piper for voice responses, and Ollama for the LLM brain — all running on my own machines, stitched together with the Wyoming protocol. I could literally talk to my smart home, and it talked back. All offline, all private.</p><p><a href="https://mastodon.social/tags/SelfHosting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SelfHosting</span></a> <a href="https://mastodon.social/tags/HomeAssistant" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HomeAssistant</span></a> <a href="https://mastodon.social/tags/VoiceAssistant" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VoiceAssistant</span></a> <a href="https://mastodon.social/tags/LocalAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LocalAI</span></a> <a href="https://mastodon.social/tags/Whisper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Whisper</span></a> <a href="https://mastodon.social/tags/Piper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Piper</span></a> <a href="https://mastodon.social/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a> <a href="https://mastodon.social/tags/HomeLab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HomeLab</span></a> <a href="https://mastodon.social/tags/TechDIY" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechDIY</span></a></p>
Ivan Todorov<p>Sometime back, I got obsessed with the idea of running my own voice assistant — fully local, no Google, no Amazon, no "cloud intelligence." Just me, my wife and our server(s)... </p><p>So I built Marvin.</p><p>👇</p><p><a href="https://mastodon.social/tags/SelfHosting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SelfHosting</span></a> <a href="https://mastodon.social/tags/HomeAssistant" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HomeAssistant</span></a> <a href="https://mastodon.social/tags/VoiceAssistant" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VoiceAssistant</span></a> <a href="https://mastodon.social/tags/LocalAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LocalAI</span></a> <a href="https://mastodon.social/tags/Whisper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Whisper</span></a> <a href="https://mastodon.social/tags/Piper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Piper</span></a> <a href="https://mastodon.social/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a> <a href="https://mastodon.social/tags/HomeLab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HomeLab</span></a> <a href="https://mastodon.social/tags/TechDIY" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechDIY</span></a></p>
Markus Eisele<p>Tracing the Mind of Your AI: Java Observability with Quarkus and LangChain4j<br>Instrument, trace, and monitor your AI-powered Java apps using local LLMs, Ollama, and OpenTelemetry with zero boilerplate. <br><a href="https://myfear.substack.com/p/java-ai-observability-quarkus-langchain4j" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">myfear.substack.com/p/java-ai-</span><span class="invisible">observability-quarkus-langchain4j</span></a><br><a href="https://mastodon.online/tags/Java" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Java</span></a> <a href="https://mastodon.online/tags/LangChain4j" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LangChain4j</span></a> <a href="https://mastodon.online/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ollama</span></a> <a href="https://mastodon.online/tags/OpenTelemetry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenTelemetry</span></a></p>
Replied in thread
Thomas Fricke (he/his)

@the_cjuty
@andreclaassen
@ralf_weinert

Das sieht imho so aus wie ein #ollama , in das ihr eigene Dokumente faxen, äh ich meine als PDF hochladen könnt.

Lest die Doku auf Opencode #rtfm

Das läuft lokal, wenn Ihr genug Ressourcen habt.

Fragen die offen sind:

Ist das #foss #AI? Diskussionen über Lizenzen auf dem Summit in Wien waren hart bis grenzwertig!

Was ist drin? Woher die Daten? Digitale und menschliche Lieferkette?

#clickworker ? #adolfalpha Problem ?

Schaut Euch das an 🙏

TrendingLive feeds
About