Robert Dahlke's picture

4 5 4

Robert Dahlke PRO

rbrt

·

https://www.tngtech.com

robert-dahlke

AI & ML interests

MoE Architecture, building Chimera Models, Finetuning

Recent Activity

new activity 3 days ago

tngtech/DeepSeek-R1T-Chimera:Any plans to release an updated version based on DeepSeek-V3-0526 + R1, or how to create the merge myself?

authored a paper 9 days ago

Assembly of Experts: Linear-time construction of the Chimera LLM variants with emergent and adaptable behaviors

updated a Space 9 days ago

tngtech/README

View all activity

Organizations

Articles 1

Article

33

Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time

Papers 2

arxiv:2506.14794

arxiv:2502.11096

models 0

None public yet

datasets 0

None public yet