Cond Zero's picture

12

Cond Zero

condzero

·

AI & ML interests

None yet

Recent Activity

new activity about 1 month ago

lldacing/flash-attention-windows-wheel:flash_attn-2.7.4.post1%2Bcu128torch2.8.0cxx11abiTRUE-cp312-cp312-win_amd64

new activity 5 months ago

LifuWang/DistillT5:Is this something you can do for the WAN UMT5EncoderModel?

new activity 5 months ago

HiDream-ai/HiDream-I1-Full:Why did the authors choose such a low token max_sequence_count for this model? 128 doesn't cut it. S/B at least 512 tokens. What gives?

View all activity

Organizations

None yet

condzero 's datasets

None public yet