Archives/petals
2
0
Fork 0
mirror of https://github.com/bigscience-workshop/petals synced 2024-11-16 06:12:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make even smaller readability changes

Browse Source
This commit is contained in:
Alexander Borzunov 2022-09-20 15:03:57 +04:00 committed by GitHub
parent d1b012b479
commit 640bbc38a9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -106,7 +106,7 @@ python -m cli.run_server bloom-testing/test-bloomd-560m-main --num_blocks 8 --to
This server will host 8 (out of 24) blocks of a [tiny 560M version](https://huggingface.co/bloom-testing/test-bloomd-560m-main) of the BLOOM model that was converted for Petals.
> If you'd like to run the full BLOOM straight away, please see [this instruction](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm) (you'll need several GPUs!). To run a different model, see [this wiki page](https://github.com/bigscience-workshop/petals/wiki/Run-a-custom-model-with-PETALS).
> If you'd like to run a swarm of servers with the full BLOOM straight away, please see [this instruction](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm) (you'll need several GPUs!). To run a different model, see [this wiki page](https://github.com/bigscience-workshop/petals/wiki/Run-a-custom-model-with-PETALS).
Once the server has started, it will print out a ton of information, including an important line like this:
@ -124,7 +124,7 @@ python -m cli.run_server bloom-testing/test-bloomd-560m-main --num_blocks 8 --to
```
You can assign `--initial_peers` to one or multiple addresses of other servers, not necessarily the first one.
The only requirement is that at least one of them is alive, i.e. running at the time.
The only requirement is that at least one of them is running at the time.
Before you proceed, __please run 3 servers__ for a total of 24 blocks (3x8). If you are running a different model,
make sure your servers have enough total `--num_blocks` to cover that model.