Cerebras

cerebras's activity

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

lazarevich 

in cerebras/Qwen3-Coder-REAP-25B-A3B 1 day ago

model.safetensors.index.json missing?

1

#8 opened 1 day ago by

samlam0206

lazarevich 

updated a model 1 day ago

cerebras/Qwen3-Coder-REAP-25B-A3B

Text Generation • Updated about 1 month ago • 4.92k • 41

lazarevich 

updated a collection 2 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 17 items • Updated 2 days ago • 43

lazarevich 

in cerebras/MiniMax-M2-REAP-162B-A10B 2 days ago

We need 50 or 60% expert pruning please

4

#3 opened 5 days ago by

hxssgaa

lazarevich 

updated 3 models 3 days ago

cerebras/MiniMax-M2-REAP-139B-A10B

Text Generation • 139B • Updated 3 days ago • 442 • 8

cerebras/MiniMax-M2-REAP-172B-A10B

Text Generation • 173B • Updated 5 days ago • 173 • 13

cerebras/MiniMax-M2-REAP-162B-A10B

Text Generation • 162B • Updated 5 days ago • 3.15k • 63

lazarevich 

published a model 3 days ago

cerebras/MiniMax-M2-REAP-139B-A10B

Text Generation • 139B • Updated 3 days ago • 442 • 8

lazarevich 

in cerebras/MiniMax-M2-REAP-162B-A10B 3 days ago

thinking disables tools

5

#6 opened 3 days ago by

ktsaou

Tool Use Benchmarks

1

#2 opened 5 days ago by

louis-szeto

lazarevich 

in cerebras/MiniMax-M2-REAP-172B-A10B 3 days ago

Tokenizer is wrong

1

#1 opened 3 days ago by

ilintar

vithursant 

in cerebras/Qwen3-Coder-REAP-25B-A3B 5 days ago

minimax m2 REAP + unsloth 1,1.58,2,4bit dynamic ggufs targeting compute constrained context lengths

1

#6 opened 19 days ago by

TimeLordRaps

vithursant 

in cerebras/GLM-4.5-Air-REAP-82B-A12B 5 days ago

Request to REAP MiniMaxAI/MiniMax-M2

👍 5

1

#15 opened 22 days ago by

blackcat1402

lazarevich 

in cerebras/Kimi-Linear-REAP-35B-A3B-Instruct 5 days ago

MiniMax M2

6

#4 opened 8 days ago by

louis-szeto

lazarevich 

updated a collection 5 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 17 items • Updated 2 days ago • 43

lazarevich 

published 2 models 5 days ago

cerebras/MiniMax-M2-REAP-162B-A10B

Text Generation • 162B • Updated 5 days ago • 3.15k • 63

cerebras/MiniMax-M2-REAP-172B-A10B

Text Generation • 173B • Updated 5 days ago • 173 • 13

lazarevich 

updated a collection 13 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 17 items • Updated 2 days ago • 43

lazarevich 

updated a model 13 days ago

cerebras/Kimi-Linear-REAP-35B-A3B-Instruct

Text Generation • 35B • Updated 14 days ago • 5.57k • 42