Leo's picture

Leo PRO

leideng

·

https://leideng.github.io/

AI & ML interests

Efficient AI, Sparse Attention

Recent Activity

updated a collection about 13 hours ago

authored a paper about 19 hours ago

Extending Context Window of Large Language Models via Semantic Compression

authored a paper about 19 hours ago

Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory

View all activity

Organizations

None yet

leideng 's datasets 12

leideng/Dolci-Think-SFT-7B-4K-Plus

Viewer • Updated Apr 19 • 3.63M • 1.69k

leideng/Dolci-Instruct-SFT-4K-Plus

Viewer • Updated Apr 19 • 2.19M • 842

leideng/Dolci-Think-RL-7B-4K-Plus

Viewer • Updated Apr 19 • 102k • 39

leideng/Dolci-Instruct-RL-4K-Plus

Viewer • Updated Apr 19 • 170k • 48

leideng/Dolci-Think-DPO-7B-4K-Plus

Viewer • Updated Apr 19 • 150k • 100

leideng/Dolci-Instruct-DPO-4K-Plus

Viewer • Updated Apr 19 • 260k • 289

leideng/longbench-v2-view

Viewer • Updated Apr 11 • 1.51k • 67

leideng/longbench-view

Viewer • Updated Apr 11 • 8.42k • 214

leideng/nanochat-ascend-dataset

Viewer • Updated Apr 6 • 72.3k • 446

leideng/nanochat-ascend-eval

Viewer • Updated Apr 6 • 272k • 227

leideng/nanochat-ascend-task

Viewer • Updated Apr 5 • 617k • 317

leideng/karpathy-identity-conversations

Viewer • Updated Apr 5 • 1k • 22