Yu Zhang

yzhangcs's activity

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

liked a model about 8 hours ago

moonshotai/Kimi-K2-Thinking

Text Generation • Updated about 8 hours ago • 117 • 221

commented a paper about 11 hours ago

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published 7 days ago • 96 •

3

upvoted an article 1 day ago

view article

Article

Ring-flash-linear-2.0: A Highly Efficient Hybrid Architecture for Test-Time Scaling

By and 8 others •

28 days ago

• 11

authored a paper 3 days ago

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published 7 days ago • 96

New activity in moonshotai/Kimi-K2-Instruct 3 days ago

Any plan to support MTP?

4

#52 opened 3 months ago by

1000Xia

updated a collection 4 days ago

Moonlight-A3B

Collection

Moonshot's Compute-efficient MoE LLM, first Scaling Up of Muon Optimizer • 3 items • Updated 4 days ago • 7

New activity in moonshotai/Kimi-Linear-48B-A3B-Instruct 5 days ago

Some metrics

➕ 3

4

#3 opened 7 days ago by

louis-szeto

New activity in moonshotai/Kimi-Linear-48B-A3B-Base 5 days ago

Adding `transformers` as the model library

#1 opened 7 days ago by

ariG23498

liked 2 models 5 days ago

moonshotai/Kimi-Linear-48B-A3B-Base

Text Generation • 49B • Updated 6 days ago • 465 • 49

moonshotai/Kimi-Linear-48B-A3B-Instruct

Text Generation • 49B • Updated 6 days ago • 86.3k • 393

New activity in moonshotai/Kimi-Linear-48B-A3B-Instruct 5 days ago

Added transformers Library

🔥 1

2

#5 opened 7 days ago by

Daemontatox

updated 2 models 6 days ago

moonshotai/Kimi-Linear-48B-A3B-Base

Text Generation • 49B • Updated 6 days ago • 465 • 49

moonshotai/Kimi-Linear-48B-A3B-Instruct

Text Generation • 49B • Updated 6 days ago • 86.3k • 393

New activity in moonshotai/Kimi-Linear-48B-A3B-Instruct 6 days ago

Local Installation Video and Testing - Step by Step

👍 6

1

#4 opened 7 days ago by

fahdmirzac

why do we still need qk_rope_head_dim when using Nope

1

#6 opened 6 days ago by

jimmyhbx

upvoted a paper 7 days ago

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published 7 days ago • 96

updated a collection 7 days ago

Kimi-Linear-A3B

Collection

Moonshot's experimental MoE model with Kimi Delta Attention • 3 items • Updated 6 days ago • 10

New activity in moonshotai/Kimi-Linear-48B-A3B-Instruct 7 days ago

Fix LaTeX rendering issue on README.md

1

#2 opened 7 days ago by

C10X