33 32

AItomek ;P

altomek

altomek

AI & ML interests

MLOps, Polish LLMs

Recent Activity

updated a model 3 days ago

altomek/Lo101-3B-AnD-GGUF

updated a collection 3 days ago

Quants for ARM

updated a model 3 days ago

altomek/Lo101-3B-AnD

View all activity

Organizations

altomek's activity

updated a model 3 days ago

altomek/Lo101-3B-AnD-GGUF

Text Generation • Updated 3 days ago • 66

updated a collection 3 days ago

Quants for ARM

Collection

11 items • Updated 3 days ago • 1

updated a model 3 days ago

altomek/Lo101-3B-AnD

Text Generation • Updated 3 days ago • 20

liked a model 3 days ago

qingy2024/GRMR-2B-Instruct

Text Generation • Updated 25 days ago • 134 • 15

updated 2 models 11 days ago

altomek/Mixtral-8x7B-Instruct-v0.1-GGUF

Updated 11 days ago • 49

altomek/WizardLM-33B-V1.0-Uncensored-GGUF

Updated 11 days ago • 146

New activity in mergekit-community/QwQ-32B-Preview-Instruct-Coder 13 days ago

....... .....

#1 opened 13 days ago by

altomek

replied to bartowski's post 27 days ago

Nice, thanks for the link! Yes, just wanted to be sure I need software update to make use of this. Looks like I may like IQ4_NL more in near future :P

replied to bartowski's post 27 days ago

Huh interesting, however all inference engines need to adapt newer llama.cpp version correct? Q4_0 and IQ4_NL? Just scrolled throught the pull request. How do you know IQ4_NL should work this way also?

liked 2 models about 1 month ago