I have released LLama2.c64 - an LLM running on a C64 with 2MB REU. It runs the Llama2 LLM architecture, using the tokenizer and weights from the Tinystories 260K model.
It's a storytelling model that tries its best to spin your prompt into a story, as if told by a kindergarten child. It will generate one output token about every 8 minutes.
β¦
πΊπ¦ #NowPlaying on #BBC6Music's #HuwStephens
Sister Nancy:
π΅ Bam Bam
#SisterNancy
https://dubstorerecords.bandcamp.com/track/sister-nancy-bam-bam
https://open.spotify.com/track/1p2ea5Dy0tOnt9q4wfy4aX
πΊπ¦ #NowPlaying on #BBC6Music's #HuwStephens
Sister Nancy:
π΅ Bam Bam
#SisterNancy
https://dubstorerecords.bandcamp.com/track/sister-nancy-bam-bam
https://open.spotify.com/track/1p2ea5Dy0tOnt9q4wfy4aX