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 4 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 10 days ago

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

updated a Space 10 days ago

tngtech/README

View all activity

Organizations

upvoted 2 articles 2 months ago

Article

Finetuning olmOCR to be a faithful OCR-Engine

By

and 1 other •

Apr 22

• 18

Article

Prefill and Decode for Concurrent Requests - Optimizing LLM Performance

By

•

Apr 16

• 18

upvoted an article 3 months ago

Article

Efficient Request Queueing – Optimizing LLM Performance

By

•

Apr 2

• 12

upvoted a paper 4 months ago

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

Paper • 2502.11096 • Published Feb 16 • 2

upvoted an article 4 months ago

Article

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

By

and 4 others •

Feb 18

• 33