Robert Dahlke PRO

rbrt's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 17 days ago

tngtech/DeepSeek-TNG-R1T2-Chimera

Text Generation • 685B • Updated 1 day ago • 4.84k • 230

New activity in tngtech/DeepSeek-TNG-R1T2-Chimera 23 days ago

R1Tx?

5

#14 opened 26 days ago by

Blazgo

New activity in tngtech/DeepSeek-TNG-R1T2-Chimera 28 days ago

How is the style?

1

#3 opened about 1 month ago by

ChuckMcSneed

Where to access other than Chutes.

4

#8 opened about 1 month ago by

cinnybun02

Test

#13 opened 28 days ago by

leyra2025

Request: DOI

#10 opened 30 days ago by

samwisejones

New activity in tngtech/DeepSeek-R1T-Chimera about 1 month ago

Chimera not separating reasoning from response

19

#3 opened 3 months ago by

SanityInMotion

New activity in tngtech/DeepSeek-TNG-R1T2-Chimera about 1 month ago

AIME24, AIME25 and GPQA-Diamond results

2

#5 opened about 1 month ago by

ID0M

updated a Space about 1 month ago

Running

README

🚀

TNG on huggingface

liked 2 models about 1 month ago

unsloth/DeepSeek-TNG-R1T2-Chimera-BF16

Text Generation • 684B • Updated Jul 4 • 31 • 3

unsloth/DeepSeek-TNG-R1T2-Chimera

Text Generation • 685B • Updated Jul 3 • 52 • 6

New activity in tngtech/DeepSeek-TNG-R1T2-Chimera about 1 month ago

Missing `model.safetensors.index.json`

2

#2 opened about 1 month ago by

danielhanchen

liked a model about 1 month ago

tngtech/DeepSeek-TNG-R1T2-Chimera

Text Generation • 685B • Updated 1 day ago • 4.84k • 230

published a model about 1 month ago

tngtech/DeepSeek-TNG-R1T2-Chimera

Text Generation • 685B • Updated 1 day ago • 4.84k • 230

New activity in tngtech/DeepSeek-R1T-Chimera about 1 month ago

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

14

#4 opened 2 months ago by

Lissanro

authored a paper about 2 months ago

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

Paper • 2506.14794 • Published May 31 • 1

New activity in tngtech/DeepSeek-R1T-Chimera 3 months ago

Paid version?

1

#2 opened 3 months ago by

Blazgo

updated a model 3 months ago

tngtech/DeepSeek-R1T-Chimera

Text Generation • 685B • Updated about 1 month ago • 1.37k • 262

New activity in tngtech/DeepSeek-R1T-Chimera 3 months ago

Questions on how routed experts are merged

👍 👀 17

8

#1 opened 3 months ago by

chuhac

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

view reply

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: