Recent searches

No recent searches

Search options

Only available when logged in.
med-mastodon.com is one of the many independent Mastodon servers you can use to participate in the fediverse.
Medical community on Mastodon

Administered by:

Server stats:

345
active users

med-mastodon.com: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.5

#starcoder

0 posts0 participants0 posts today
GOMOOT :mastodon:<p>💡 Stable Code 3b, una LLM compatta per programmatori <br>Stability ha rilasciato Stable Code 3b, una piccola LLM di soli 3 miliardi di dati che può essere eseguita anche su laptop senza GPU<br><a href="https://gomoot.com/stable-code-3b-una-llm-compatta-per-programmatori" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">gomoot.com/stable-code-3b-una-</span><span class="invisible">llm-compatta-per-programmatori</span></a><br><a href="https://mastodon.uno/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.uno/tags/coding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>coding</span></a> <a href="https://mastodon.uno/tags/ia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ia</span></a> <a href="https://mastodon.uno/tags/javascript" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>javascript</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/php" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>php</span></a> <a href="https://mastodon.uno/tags/programmazione" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>programmazione</span></a> <a href="https://mastodon.uno/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>python</span></a> <a href="https://mastodon.uno/tags/replitcode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>replitcode</span></a> <a href="https://mastodon.uno/tags/stabilityia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>stabilityia</span></a> <a href="https://mastodon.uno/tags/StableCode3b" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StableCode3b</span></a> <a href="https://mastodon.uno/tags/starcoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>starcoder</span></a></p>
Chuck Darwin<p>Meta today open-sourced <a href="https://c.im/tags/Code" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Code</span></a> <a href="https://c.im/tags/Llama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Llama</span></a>, a machine learning system that can generate and explain code in natural language — specifically English.</p><p>Akin to GitHub <a href="https://c.im/tags/Copilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Copilot</span></a> and Amazon <a href="https://c.im/tags/CodeWhisperer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CodeWhisperer</span></a>, as well as open source AI-powered code generators like <a href="https://c.im/tags/StarCoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StarCoder</span></a>, <a href="https://c.im/tags/StableCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StableCode</span></a> and <a href="https://c.im/tags/PolyCoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PolyCoder</span></a>, <a href="https://c.im/tags/CodeLlama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CodeLlama</span></a> can complete code and debug existing code across a range of programming languages</p><p><a href="https://techcrunch.com/2023/08/24/meta-releases-code-llama-a-code-generating-ai-model/" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">techcrunch.com/2023/08/24/meta</span><span class="invisible">-releases-code-llama-a-code-generating-ai-model/</span></a></p>
Oliver Sampson<p>I started using <span class="h-card"><a href="https://mas.to/@huggingface" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>huggingface</span></a></span> <a href="https://sigmoid.social/tags/StarCoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StarCoder</span></a>, and I'm still trying to get used to using it. Very cool tech in general, but today was a miraculous fail! Thanks for the quick laugh!</p>
Juan Luis<p>Noticias sobre Python y Datos de la semana, episodio 76 🐍⚙️</p><p>En resumen: Edición ultrarrápida de domingo por la tarde: versiones nuevas de numba, statsmodels y geopandas, por qué no usar leyendas en matplotlib, y primeras pruebas con StarCoder.</p><p><a href="https://buttondown.email/astrojuanlu/archive/episodio-76/" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">buttondown.email/astrojuanlu/a</span><span class="invisible">rchive/episodio-76/</span></a></p><p>Apoya el noticiero suscribiéndote por correo 📬</p><p><a href="https://social.juanlu.space/tags/noticieropythonydatos" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>noticieropythonydatos</span></a> <a href="https://social.juanlu.space/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>python</span></a> <a href="https://social.juanlu.space/tags/pydata" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pydata</span></a> <a href="https://social.juanlu.space/tags/numba" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>numba</span></a> <a href="https://social.juanlu.space/tags/statsmodels" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>statsmodels</span></a> <a href="https://social.juanlu.space/tags/geopandas" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>geopandas</span></a> <a href="https://social.juanlu.space/tags/matplotlib" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>matplotlib</span></a> <a href="https://social.juanlu.space/tags/starcoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>starcoder</span></a> <a href="https://social.juanlu.space/tags/polars" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>polars</span></a> </p><p>¡Sigue a <span class="h-card"><a href="https://fosstodon.org/@numba" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>numba</span></a></span> y <span class="h-card"><a href="https://fosstodon.org/@geopandas" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>geopandas</span></a></span> en Mastodon!</p>
Taras Novak 🇺🇦<p>Took <a href="https://vis.social/tags/StarCoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StarCoder</span></a> from <a href="https://vis.social/tags/BigCodeProject" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BigCodeProject</span></a> for a spin today. Used 🤗 <a href="https://vis.social/tags/VSCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VSCode</span></a> autocomplete extension to generate a bunch of sample employees <a href="https://vis.social/tags/DuckDB" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DuckDB</span></a> SQL queries for the next <a href="https://vis.social/tags/DuckDBPro" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DuckDBPro</span></a> Tools update. <a href="https://vis.social/tags/DataTools" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataTools</span></a> 🔬 ...</p><p><a href="https://www.linkedin.com/feed/update/urn:li:activity:7060961253258625024/" rel="nofollow noopener" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">linkedin.com/feed/update/urn:l</span><span class="invisible">i:activity:7060961253258625024/</span></a></p>
Chuck Darwin<p><a href="https://c.im/tags/BigCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BigCode</span></a> is an open scientific collaboration working on responsible training of large language models for coding applications. </p><p>In this organization you can find the artefacts of this collaboration:<br>👉 <a href="https://c.im/tags/StarCoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StarCoder</span></a>, a state-of-the-art language model for code, <br>👉 The <a href="https://c.im/tags/Stack" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Stack</span></a>, the largest available pretraining dataset with perimssive code, and 👉 <a href="https://c.im/tags/SantaCoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SantaCoder</span></a>, a 1.1B parameter model for code.</p><p><a href="https://c.im/tags/StarCoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StarCoder</span></a> is a 15.5B parameters language model for code trained for 1T tokens on 80+ programming languages. <br>It uses MQA for efficient generation, has 8,192 tokens context window and can do fill-in-the-middle.</p><p>Chat with StarCoder here: <a href="https://huggingface.co/chat/?model=bigcode/starcoder" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">huggingface.co/chat/?model=big</span><span class="invisible">code/starcoder</span></a></p><p><a href="https://huggingface.co/bigcode" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">huggingface.co/bigcode</span><span class="invisible"></span></a></p>
Tero Keski-Valkama<p><a href="https://rukii.net/tags/BigCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BigCode</span></a> <a href="https://rukii.net/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a></p><p>"<a href="https://rukii.net/tags/StarCoder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StarCoder</span></a> is a 15.5B parameters language model for code trained for 1T tokens on 80+ programming languages. It uses MQA for efficient generation, has 8,192 tokens context window and can do fill-in-the-middle."</p><p><a href="https://huggingface.co/bigcode" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">huggingface.co/bigcode</span><span class="invisible"></span></a></p>
TrendingLive feeds
About