Lukas Schneider

LukasSchneider

3 1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

RoboICL: Embodied In-Context Learning with GPT-6 Astra

liked a model about 1 year ago

IntervitensInc/pangu-pro-moe-model

reacted to AdinaY's post with 🔥 about 1 year ago

Pangu Pro MoE 🔥 Huawei's first open model! Paper: https://huggingface.co/papers/2505.21411 Model: https://gitcode.com/ascend-tribe/pangu-pro-moe-model ✨ MoGE: Mixture of Grouped Experts ✨ 16B activated params - 48 layers ✨ Trained on 15T tokens ✨ Natively optimized for Ascend hardware

View all activity

Organizations

None yet

upvoted a paper 1 day ago

RoboICL: Embodied In-Context Learning with GPT-6 Astra

Paper • 2609.34261 • Published 2 days ago • 13

liked a model about 1 year ago

IntervitensInc/pangu-pro-moe-model

Text Generation • 72B • Updated Jul 9, 2025 • 124 • 45

reacted to AdinaY's post with 🔥 about 1 year ago

Post

1272

Pangu Pro MoE 🔥 Huawei's first open model!

Paper:
Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity (2505.21411)
Model:
https://gitcode.com/ascend-tribe/pangu-pro-moe-model

✨ MoGE: Mixture of Grouped Experts
✨ 16B activated params - 48 layers
✨ Trained on 15T tokens
✨ Natively optimized for Ascend hardware

1 reply

·

upvoted 2 papers over 1 year ago

Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity

Paper • 2505.21411 • Published May 27, 2025 • 17

Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Paper • 2505.04519 • Published May 7, 2025 • 5