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

communick@poweruser.forum

Mozilla Llamafile - bundling one model & llama.cpp into a single executable (alien.top)

submitted 11 months ago by Danmoreng@alien.top to c/localllama@poweruser.forum

4 comments fedilink hide all child comments

Just read about this project on Twitter and it sounds really interesting:

https://github.com/mozilla-Ocho/llamafile

What do guys think, might be even more simple than Ollama?

you are viewing a single comment's thread
view the rest of the comments

[–] silenceimpaired@alien.top 1 points 11 months ago

Exciting and worrying… I have gone to great efforts to use safetensors… I would have to see every model packaged in executable format… but then again I have seen comments about llama.cpp behavior changing for the same model and settings (not sure if it is true but that could be bad)