sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Server stats:

599
active users

#deepspeed

0 posts0 participants0 posts today
michabbb<p>Introducing Phind-405B and faster, high quality <a href="https://social.vivaldi.net/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> answers for everyone</p><p>🚀 Phind-405B: New flagship <a href="https://social.vivaldi.net/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a>, based on Meta Llama 3.1 405B, designed for programming &amp; technical tasks. <a href="https://social.vivaldi.net/tags/Phind405B" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Phind405B</span></a></p><p>⚡ 128K tokens, 32K context window at launch, 92% on HumanEval, great for web app design. <a href="https://social.vivaldi.net/tags/Programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Programming</span></a> <a href="https://social.vivaldi.net/tags/AIModel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIModel</span></a></p><p>💡 Trained on 256 H100 GPUs with FP8 mixed precision, 40% memory reduction. <a href="https://social.vivaldi.net/tags/DeepSpeed" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepSpeed</span></a> <a href="https://social.vivaldi.net/tags/FP8" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FP8</span></a></p><p>⚡ Phind Instant Model: Super fast, 350 tokens/sec, based on Meta Llama 3.1 8B. <a href="https://social.vivaldi.net/tags/PhindInstant" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PhindInstant</span></a></p><p>🚀 Runs on NVIDIA TensorRT-LLM with flash decoding, fused CUDA kernels. <a href="https://social.vivaldi.net/tags/NVIDIA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NVIDIA</span></a> <a href="https://social.vivaldi.net/tags/GPUs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GPUs</span></a></p><p>🔍 Faster Search: Prefetches results, saves up to 800ms latency, better embeddings. <a href="https://social.vivaldi.net/tags/FastSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FastSearch</span></a></p><p>👨‍💻 Goal: Help developers experiment faster, new features coming soon! <a href="https://social.vivaldi.net/tags/DevTools" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DevTools</span></a> <a href="https://social.vivaldi.net/tags/Innovation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Innovation</span></a></p><p><a href="https://www.phind.com/blog/introducing-phind-405b-and-better-faster-searches" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phind.com/blog/introducing-phi</span><span class="invisible">nd-405b-and-better-faster-searches</span></a></p>