User avatar
Two Hollywood Phonies @autumn@cafe.autumn.town
1y
i should do this but instead of using gemma3:27B or llama3.1:8B using qwen3:0.6b (thinking model)

medium.com/data-science-collective/train-llms-to-talk-like-you-on-social-media-using-consumer-hardware-c88750a56e6d
2
0
2
0
User avatar
iris🇦🇱 @authen@brain.worm.pink
1y
@autumn was gonna do this but im not reading allat
1
0
1
0
User avatar
Two Hollywood Phonies @autumn@cafe.autumn.town
1y
@authen i think you would need your own gpu too lmao
1
0
2
0
User avatar
no longer kopper @kopper@wetdry.world
1y
@autumn @authen could prolly throw it into colab if that's still a thing not killed by crypto miners and whatever
0
0
2
0
User avatar
Two Hollywood Phonies @autumn@cafe.autumn.town
1y
oh but then i would have to run it on my raspberry pi i'm fine actually
0
0
2
0