3 5 4

Robert Dahlke PRO

rbrt

https://www.tngtech.com

AI & ML interests

None yet

Recent Activity

new activity 7 days ago

tngtech/DeepSeek-R1T-Chimera:Paid version?

updated a model 20 days ago

tngtech/DeepSeek-R1T-Chimera

new activity 22 days ago

tngtech/DeepSeek-R1T-Chimera:Questions on how routed experts are merged

View all activity

Organizations

rbrt's activity

New activity in tngtech/DeepSeek-R1T-Chimera 7 days ago

Paid version?

#2 opened 19 days ago by

Blazgo

updated a model 20 days ago

tngtech/DeepSeek-R1T-Chimera

Text Generation • Updated 20 days ago • 4.34k • 228

New activity in tngtech/DeepSeek-R1T-Chimera 22 days ago

Questions on how routed experts are merged

👀 🧠 17

#1 opened 28 days ago by

chuhac

commented on Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time 23 days ago

We published the experts that we switched off in the paper (see below). The method to switch them off works at inference time, so no need to upload new weights:

liked a model 24 days ago

deepseek-ai/DeepSeek-Prover-V2-671B

Text Generation • Updated 25 days ago • 10.7k • • 783

liked a model 28 days ago

tngtech/DeepSeek-R1T-Chimera

Text Generation • Updated 20 days ago • 4.34k • 228

published a model 28 days ago

tngtech/DeepSeek-R1T-Chimera

Text Generation • Updated 20 days ago • 4.34k • 228

updated a Space about 1 month ago

README

🚀

TNG on huggingface

upvoted 2 articles about 1 month ago

Article

Finetuning olmOCR to be a faithful OCR-Engine

and 1 other •

Apr 22

• 18

Article

Prefill and Decode for Concurrent Requests - Optimizing LLM Performance

•

Apr 16

• 13

upvoted an article about 2 months ago

Article

Efficient Request Queueing – Optimizing LLM Performance

•

Apr 2

• 12

liked a model 2 months ago

deepseek-ai/DeepSeek-V3-0324

Text Generation • Updated Mar 27 • 443k • • 2.93k

updated a model 2 months ago

tngtech/OLMo-2-Instruct-Math-32B

Text Generation • Updated Apr 17 • 13 • 7

liked a model 2 months ago

tngtech/OLMo-2-Instruct-Math-32B

Text Generation • Updated Apr 17 • 13 • 7

authored a paper 3 months ago

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

Paper • 2502.11096 • Published Feb 16 • 2

commented 2 papers 3 months ago

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

Paper • 2502.11096 • Published Feb 16 • 2 •

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

Paper • 2502.11096 • Published Feb 16 • 2 •

upvoted a paper 3 months ago

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

Paper • 2502.11096 • Published Feb 16 • 2

published a Space 3 months ago

README

🚀

TNG on huggingface

commented on Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time 3 months ago

That's a bit scary. Because listening to it, we assumed it read the paper.

So it seems there are more hallucinations than we initially thought. Funnily, quite a few of them it guessed correctly.