Shwai He

Shwai's activity

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

upvoted a paper 10 days ago

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

Paper • 2506.01713 • Published 12 days ago • 43

liked a model 3 months ago

Qwen/QwQ-32B

Text Generation • Updated Mar 11 • 299k • • 2.78k

upvoted a collection 3 months ago

computation

Collection

this is for Mixture of XXX • 1 item • Updated Oct 23, 2024 • 2

upvoted 2 papers 3 months ago

Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers

Paper • 2410.13184 • Published Oct 17, 2024 • 3

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts

Paper • 2503.05066 • Published Mar 7 • 4

commented a paper 3 months ago

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts

Paper • 2503.05066 • Published Mar 7 • 4 •

2

upvoted 2 papers 4 months ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 404

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Paper • 2405.04434 • Published May 7, 2024 • 21

liked 12 models 8 months ago

s1ghhh/Mistral-7B-v0.1-Drop4Attn

Updated Sep 8, 2024 • 7 • 2

s1ghhh/Llama-2-13b-Drop8Block

Updated Sep 8, 2024 • 8 • 2

s1ghhh/Llama-2-13b-Drop4Block

Updated Sep 8, 2024 • 9 • 2

s1ghhh/Llama-2-13b-Drop8Attn

Updated Sep 8, 2024 • 8 • 2

s1ghhh/Llama-2-13b-Drop4Attn

Updated Sep 8, 2024 • 8 • 2

s1ghhh/Llama-2-13b-Drop4MLP

Updated Sep 8, 2024 • 9 • 2

s1ghhh/Llama-2-13b-Drop8MLP

Updated Sep 8, 2024 • 9 • 2

s1ghhh/Mistral-7B-v0.1-Drop4Block

Updated Sep 8, 2024 • 8 • 2

s1ghhh/Mistral-7B-v0.1-Drop8Block

Updated Sep 8, 2024 • 8 • 2

s1ghhh/Mistral-7B-v0.1-Drop8Attn

Updated Sep 8, 2024 • 44 • 2

s1ghhh/Mistral-7B-v0.1-Drop4MLP

Updated Sep 8, 2024 • 8 • 2

s1ghhh/Mistral-7B-v0.1-Drop8MLP

Updated Sep 8, 2024 • 8 • 2