view post Post 1666 Mini-QwQ an edge device friendly reasoning model distilled from QwQ-32B ๐ค: kz919/QwQ-0.5B-Distilled-SFT๐ฌ ๐ฌ ๐บ ๐ซ: kz919/QwQ-0.5B-Distilled-SFT-gguf๐ค: kz919/Mini-QwQ See translation ๐ 7 7 + Reply
Cautious Optimizers: Improving Training with One Line of Code Paper โข 2411.16085 โข Published Nov 25, 2024 โข 21
view post Post 1608 Just for the meme.But the clear lesson I learnt from building these demos are, the more powerful the underlying base model is, the closer you will get to GPT4o1. CoT is nothing more than simply inducing the latent reasoning capability from the model. kz919/GPT4-O1-Proximas ๐ 6 6 ๐ฅ 2 2 ๐ 1 1 + Reply
view post Post 1921 https://huggingface.co/spaces/kz919/Llama3.1-Instruct-O1 ๐ 5 5 ๐ฅ 2 2 + Reply
view post Post 2462 "It's Sunday night, fancy a game?"https://kz919-can-you-beat-405b-in-chess.hf.space/built with the one and only SN fast API:https://sambanova.ai/fast-api?api_ref=907266 7 replies ยท ๐ง 8 8 ๐ฅ 2 2 + Reply
view post Post 647 Good lord... Spent almost a day debugging this and it turns out it was an issue of gradio update incompatible with the new fastapi.https://discuss.huggingface.co/t/huggingface-space-failed-after-working-initially/105514/8Finally got it back online! Come chat with your favorite anime characters here: kz919/Persona-AI ๐ 3 3 + Reply
view post Post 1604 Spent a few minutes to build an alternative to Character AI on top of llama3.1 405B through SambaNova's super fast inference API Space: kz919/Persona-AIAPI referral link: https://sambanova.ai/fast-api?api_ref=907266 3 replies ยท ๐ฅ 3 3 ๐ 3 3 ๐ 2 2 ๐ค 2 2 ๐คฏ 2 2 ๐ง 2 2 + Reply
view post Post 1698 The only 405B spaces still freely accessible are powered by SN fast api. xianbao/SambaNova-fasthttps://sambanova.ai/fast-api?api_ref=907266 ๐ 6 6 ๐ฅ 4 4 ๐ค 2 2 ๐ 1 1 + Reply
DataComp-LM: In search of the next generation of training sets for language models Paper โข 2406.11794 โข Published Jun 17, 2024 โข 54
SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts Paper โข 2405.07518 โข Published May 13, 2024 โข 28
SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts Paper โข 2405.07518 โข Published May 13, 2024 โข 28