Join us as we explore the refusal in LLMs, release the Snowflake Arctic Instruct 128x3B MoE, and unveil the Phi-3 Mini model that will blow your mind. We even have a Llama3 70B pruned to 42B parameters – because why not?
But that’s not all! Our server is filled with FAQs, glossaries, links, and benchmarks that will make your head spin. Chatbot Arena, Programming challenges, and Censorship leaderboards await you, along with tools like the Alpha Calculator, VRAM Calculator, and Sampler visualizer.
So come on in and join the madness! Build, explore, and conquer with us as we dive deep into the world of local language models. Who knows, you might even discover the secret to unlocking the ultimate Llama power!