Sascha Wageringel

warlock76

4

warlock76

AI & ML interests

None yet

Recent Activity

new activity 13 days ago

Qwen/Qwen3.8-27B:needs "keep model in memory" enabled for some obscure reason or loading it will fail with a cache memory issue

new activity over 1 year ago

google/gemma-3-4b-it:VRAM not freed during long generations (Gemma, max_new_tokens=3000)

new activity over 2 years ago

upstage/SOLAR-10.7B-Instruct-v1.0:I feel that this 11B model is smarter and hallucinates less than other leaders

View all activity

Organizations

None yet

New activity in Qwen/Qwen3.8-27B 13 days ago

needs "keep model in memory" enabled for some obscure reason or loading it will fail with a cache memory issue

#188 opened 13 days ago by

New activity in google/gemma-3-4b-it over 1 year ago

VRAM not freed during long generations (Gemma, max_new_tokens=3000)

#29 opened over 1 year ago by

New activity in upstage/SOLAR-10.7B-Instruct-v1.0 over 2 years ago

I feel that this 11B model is smarter and hallucinates less than other leaders

#9 opened almost 3 years ago by

New activity in Xwin-LM/Xwin-LM-13B-V0.2 almost 3 years ago

You're insane

#1 opened almost 3 years ago by