Skip to content
Better HN
Top
New
Best
Ask
Show
Jobs
Search
⌘K
Directly run and investigate Llama models locally with only PyTorch
(opens in new tab)
(github.com)
3 points
anordin95
1y ago
1 comments
Share
Directly run and investigate Llama models locally with only PyTorch | Better HN
1 comments
default
newest
oldest
anordin95
OP
1y ago
There are other popular ways to invoke these models, such as Ollama and Hugging-Face's general API package: transformers, but those hide the interesting details behind an API. Peel back the layers to poke, prod and understand!
j
/
k
navigate · click thread line to collapse