Hacker News new | ask | show | jobs
by adt 335 days ago
No.

At 1T MoE on 15.5T tokens, K2 is one of the largest open source models to date. But BAAI's TeleFM is 1T dense on 15.7T tokens: https://huggingface.co/CofeAI/Tele-FLM-1T

You can always check here: https://lifearchitect.ai/models-table/