Ivan Lazarevich

lazarevich's activity

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

New activity in cerebras/Qwen3-Coder-REAP-25B-A3B 16 days ago

model.safetensors.index.json missing?

1

#8 opened 16 days ago by

samlam0206

updated a model 16 days ago

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

Text Generation • Updated Oct 20 • 8.71k • 50

updated a collection 18 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 17 items • Updated 18 days ago • 50

New activity in cerebras/MiniMax-M2-REAP-162B-A10B 18 days ago

We need 50 or 60% expert pruning please

4

#3 opened 20 days ago by

hxssgaa

updated 3 models 18 days ago

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

Text Generation • 139B • Updated 18 days ago • 1.69k • 15

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

Text Generation • 173B • Updated 21 days ago • 885 • 15

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

Text Generation • 162B • Updated 21 days ago • 4.31k • 71

published a model 18 days ago

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

Text Generation • 139B • Updated 18 days ago • 1.69k • 15

New activity in cerebras/MiniMax-M2-REAP-162B-A10B 18 days ago

thinking disables tools

5

#6 opened 18 days ago by

ktsaou

Tool Use Benchmarks

1

#2 opened 20 days ago by

louis-szeto

New activity in cerebras/MiniMax-M2-REAP-172B-A10B 18 days ago

Tokenizer is wrong

1

#1 opened 18 days ago by

ilintar

New activity in cerebras/Kimi-Linear-REAP-35B-A3B-Instruct 21 days ago

MiniMax M2

6

#4 opened 23 days ago by

louis-szeto

updated a collection 21 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 17 items • Updated 18 days ago • 50

published 2 models 21 days ago

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

Text Generation • 162B • Updated 21 days ago • 4.31k • 71

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

Text Generation • 173B • Updated 21 days ago • 885 • 15

updated a collection 29 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 17 items • Updated 18 days ago • 50

updated a model 29 days ago

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

Text Generation • 35B • Updated 29 days ago • 6.34k • 51

published a model 29 days ago

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

Text Generation • 35B • Updated 29 days ago • 6.34k • 51

New activity in cerebras/Qwen3-Coder-REAP-25B-A3B about 1 month ago

minor typo

#4 opened about 1 month ago by

owao