this post was submitted on 30 Oct 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] lakolda@alien.top 1 points 1 year ago (2 children)

LLMZip achieves SOTA compression by a large margin.

[–] ashutrv@alien.top 1 points 1 year ago (1 children)

Very interesting 🤔 On what kind of data the compression is performing? Any progress in informational videos? I am working on building a smart media format too

[–] lakolda@alien.top 1 points 1 year ago

The original LLMZip paper mainly focused on text compression. A later work (I forget the name) used an LLM trained on byte tokens. This allowed it to compress not just text, but any file format. I think it may have been Google who published that particular paper… Very impressive though.