Sadegh
@sadegh7171
Deepseek released their flagship model, v3, a 607B mixture-of-experts model with 37B active parameters. Currently, it is the best open-source model, beating Llama 3.1 405b, Qwen, and Mistral. It is on par with OpenAI GPT-4o and Claude 3.5 Sonnet from the benchmarks. The first model performs on par and better at some tasks than the big closed models. TL;DR
1 reply
0 recast
4 reactions
Farshad 🍖 🎩💊🎭🐹
@farshadtrader1
This is amazing Is this about AI? 31 $DEGEN
0 reply
0 recast
0 reaction
🦋 Roya 🦋
@royadelsa
Very good 50 $DEGEN
0 reply
0 recast
1 reaction
nopickman
@nopickman
31 $degen for you
0 reply
0 recast
0 reaction
