llama.cu

使用说明

帮助信息

cargo xtask help

Usage: xtask <COMMAND>

Commands:
  generate  text generation
  chat      chat in console
  service   web service
  help      Print this message or the help of the given subcommand(s)

Options:
  -h, --help     Print help
  -V, --version  Print version

文本生成

cargo generate --help

简写：

cargo gen --help

text generation

Usage: xtask generate [OPTIONS] <MODEL>

Arguments:
  <MODEL>

Options:
      --gpus <GPUS>
      --max-steps <MAX_STEPS>
  -p, --prompt <PROMPT>
  -t, --use-template
  -h, --help

对话

cargo chat --help

chat in console

Usage: xtask chat [OPTIONS] <MODEL>

Arguments:
  <MODEL>

Options:
      --gpus <GPUS>
      --max-steps <MAX_STEPS>
  -h, --help                   Print help

web 服务

cargo service --help

web service

Usage: xtask service [OPTIONS] --port <PORT> <MODEL>

Arguments:
  <MODEL>

Options:
      --gpus <GPUS>
      --max-steps <MAX_STEPS>
  -p, --port <PORT>
  -h, --help