Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@ytm@social.linux.pizza
2025-04-28 07:34:48

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.

Prompt: There was a
Output: There was a big car who lived in a big tree. The car was being a little girl named Lily. She had a car with a big ball and she wanted to play with it. She went to the park
Model information screen and parameters for transformer inference: temperature, top-p, output tokens. The estimated time to generate 60 tokens is about 8h
@BBC6MusicBot@mastodonapp.uk
2025-07-02 15:39:06

πŸ‡ΊπŸ‡¦ #NowPlaying on #BBC6Music's #HuwStephens
Sister Nancy:
🎡 Bam Bam
#SisterNancy
dubstorerecords.bandcamp.com/t
open.spotify.com/track/1p2ea5D

@BBC6MusicBot@mastodonapp.uk
2025-07-02 15:35:55

πŸ‡ΊπŸ‡¦ #NowPlaying on #BBC6Music's #HuwStephens
Sister Nancy:
🎡 Bam Bam
#SisterNancy
dubstorerecords.bandcamp.com/t
open.spotify.com/track/1p2ea5D