Post
mr. TIM
timkellogg.me
did:plc:ckaz32jwl6t2cno6fmuw2nhn
R1 Chimera: a model merge of the routed experts of DeepSeek R1 and V3
The resulting merged model performs as well as R1 but without the wandering thought traces. Just as smart, but faster.
https://huggingface.co/tngtech/DeepSeek-R1T-Chimera
2025-04-27T11:29:51.585Z