mirror of
https://github.com/tldr-pages/tldr.git
synced 2025-04-29 23:24:55 +02:00
29 lines
781 B
Markdown
29 lines
781 B
Markdown
|
# Accelerate
|
||
|
|
|
||
|
|
> Accelerate is a library that enables the same PyTorch code to be run across any distributed configuration.
|
||
|
|
> More information: <https://huggingface.co/docs/accelerate/index>.
|
||
|
|
|
||
|
|
- Print environment information:
|
||
|
|
|
||
|
|
`accelerate env`
|
||
|
|
|
||
|
|
- Interactively create a configuration file:
|
||
|
|
|
||
|
|
`accelerate config`
|
||
|
|
|
||
|
|
- Print the estimated GPU memory cost of running a huggingface model with different data types:
|
||
|
|
|
||
|
|
`accelerate estimate-memory {{name/model}}`
|
||
|
|
|
||
|
|
- Test an Accelerate configuration file:
|
||
|
|
|
||
|
|
`accelerate test --config_file {{path/to/config.yaml}}`
|
||
|
|
|
||
|
|
- Run a model on CPU with Accelerate:
|
||
|
|
|
||
|
|
`accelerate launch {{path/to/script.py}} {{--cpu}}`
|
||
|
|
|
||
|
|
- Run a model on multi-GPU with Accelerate, with 2 machines:
|
||
|
|
|
||
|
|
`accelerate launch {{path/to/script.py}} --multi_gpu --num_machines {{2}}`
|