Kristian Shw's picture

Kristian Shw

KristianS7

AI & ML interests

None yet

Recent Activity

new activity 7 days ago

ByteDance/Ouro-1.4B-Thinking:Fix UniversalTransformerCache.get_mask_sizes for batched generation

new activity 7 days ago

ByteDance/Ouro-2.6B-Thinking:Fix UniversalTransformerCache.get_mask_sizes for batched generation

new activity 7 days ago

ByteDance/Ouro-1.4B:Batched generation (batch_size > 1) produces incorrect outputs — possible causal mask issue?

View all activity

Organizations

None yet

KristianS7 's models 1

KristianS7/ppo-LunarLander-v2

Reinforcement Learning • Updated May 31, 2023 • 1