Boris Knyazev

bknyaz's activity

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

New activity in bknyaz/Qwen3-Next-80B-A3B-Instruct-REAM 5 days ago

Qwen3.5 122B REAM?

👍 1

2

#3 opened 24 days ago by

McG-221

New activity in SamsungSAILMontreal/Qwen3-30B-A3B-Instruct-2507-REAM 5 days ago

keep doing it!

❤️ 1

2

#4 opened 14 days ago by

pirola

commented a paper 5 days ago

REAM: Merging Improves Pruning of Experts in LLMs

Paper • 2604.04356 • Published 9 days ago • 8 •

4

New activity in bknyaz/Qwen3-Coder-Next-REAM about 2 months ago

make REAM models for exactly one-two programming languages

1

#6 opened about 2 months ago by

zotona0

New issue: naive REAM not supporting MTP?

1

#5 opened about 2 months ago by

TomLucidor

New activity in bknyaz/Qwen3-Coder-Next-REAM 2 months ago

Could more benchmarks be done on Instruction Following / Function Calling?

4

#2 opened 2 months ago by

TomLucidor

New activity in bknyaz/Qwen3-Next-80B-A3B-Instruct-REAM 2 months ago

Has REAM been checked for their resilience towards quantization?

4

#1 opened 2 months ago by

TomLucidor

New activity in bknyaz/Qwen3-Coder-Next-REAM 2 months ago

question of code

2

#4 opened 2 months ago by

Akicou

New activity in SamsungSAILMontreal/Qwen3-30B-A3B-Instruct-2507-REAM 2 months ago

Testing REAM on Kimi-Linear and Nemtron's hybrid attention models

2

#2 opened 2 months ago by

TomLucidor

New activity in SamsungSAILMontreal/Qwen3-Coder-Next-REAP 2 months ago

wrong title

2

#1 opened 2 months ago by

floory

New activity in SamsungSAILMontreal/README 2 months ago

Do you plan to test the REAM method on other models than Qwen3 ?

1

#1 opened 2 months ago by

Rebis

New activity in bknyaz/Qwen3-Next-80B-A3B-Instruct-REAM 2 months ago

Has REAM been checked for their resilience towards quantization?

4

#1 opened 2 months ago by

TomLucidor