obriand.net

technology - machine learning - datascience - computer vision - programming
Search

llama.cpp : inference of LLaMA model in pure C/C++

https://github.com/ggerganov/llama.cpp

The main goal of llama.cpp is to run the LLaMA model using 4-bit integer quantization on a MacBook

Supported platforms:

  •  Mac OS
  •  Linux
  •  Windows (via CMake)
  •  Docker

Supported models:

Tag Cloud
data visualisatoin BAM file chntpw algorithmes labels scopes temperature added script submitted gcloud celsius exchange newcomers clause multiline plots sales networking ufw runtime