2025-02-19 16:23:17 <@man2dev:fedora.im> !startmeeting testing bug#12181
2025-02-19 16:23:18 <@meetbot-stg:fedora.im> Meeting started at 2025-02-19 16:23:17 UTC
2025-02-19 16:23:18 <@meetbot-stg:fedora.im> The Meeting name is 'testing bug#12181'
2025-02-19 16:24:55 <@man2dev:fedora.im> !topic recreate issue 
2025-02-19 16:25:17 <@man2dev:fedora.im> !meetingname testing
2025-02-19 16:25:17 <@meetbot-stg:fedora.im> The Meeting Name is now testing
2025-02-19 16:25:49 <@man2dev:fedora.im> 
2025-02-19 16:25:49 <@man2dev:fedora.im> Some relevant discussions about this (haven't gone through all of it):
2025-02-19 16:25:49 <@man2dev:fedora.im> !link: https://github.com/ollama/ollama/pull/897
2025-02-19 16:25:49 <@man2dev:fedora.im> !link: https://github.com/ollama/ollama/issues/228
2025-02-19 16:25:49 <@man2dev:fedora.im> ~
2025-02-19 16:25:49 <@man2dev:fedora.im> !idea: I would like to discuss where generative models should be placed when packaged or downloaded by developers an
2025-02-19 16:25:49 <@man2dev:fedora.im> d users, respectively. For example, according to current Fedora packaging guidelines, where should Ollama, which downloads generative models, place the LLMs? While there has been some discussion on this from Ollama's side, I am unsure how the current packaging guidelines apply in this case.
2025-02-19 16:25:49 <@man2dev:fedora.im> 
2025-02-19 16:25:49 <@man2dev:fedora.im> There are some interesting ideas going around.
2025-02-19 16:25:49 <@man2dev:fedora.im> For example, changing the download location based on environment variables.
2025-02-19 16:26:32 <@man2dev:fedora.im> !endmeeting