From 15eb50b8caaea4ceaba19239fe6028ac64f9e9b7 Mon Sep 17 00:00:00 2001 From: Aleksandr Borzunov Date: Thu, 24 Nov 2022 22:03:37 +0000 Subject: [PATCH] Fix nits in readme --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 3b2d71c..1c1ba72 100644 --- a/README.md +++ b/README.md @@ -60,7 +60,7 @@ A stable version of the code and a public swarm open to everyone will be release ### 📋 Terms of use -Before using Petals to run a language model, please make sure that you are familiar with its terms of use, risks, and limitations. For BLOOM, they are described in its [model card](https://huggingface.co/bigscience/bloom) and [license](https://huggingface.co/spaces/bigscience/license). +Before using Petals to run a language model, please make sure that you are familiar with its terms of use, risks, and limitations. In case of BLOOM, they are described in its [model card](https://huggingface.co/bigscience/bloom) and [license](https://huggingface.co/spaces/bigscience/license). ### 🔒 Privacy and security @@ -101,7 +101,7 @@ For macOS, you can *probably* run everything normally if you manage to install d ## 🚀 Getting Started -This is a toy example running on a local machine without GPU and with a tiny model. +This is a toy example running on a local machine without GPU and with a tiny model. For a detailed instruction with larger models, see ["Launch your own swarm"](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm). First, run a couple of servers, each in a separate shell. To launch your first server, run: @@ -133,7 +133,7 @@ You can assign `--initial_peers` to one or multiple addresses of other servers, 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. +make sure your servers have enough total `--num_blocks` to cover that model. Once your have enough servers, you can use them to train and/or inference the model: ```python @@ -162,8 +162,8 @@ print("Gradients (norm):", model.transformer.word_embeddings.weight.grad.norm()) ``` Of course, this is a simplified code snippet. For actual training, see the example notebooks with "deep" prompt-tuning: -- Simple text semantic classification: [examples/prompt-tuning-sst2.ipynb](./examples/prompt-tuning-sst2.ipynb). -- A personified chatbot: [examples/prompt-tuning-personachat.ipynb](./examples/prompt-tuning-personachat.ipynb). +- Simple text semantic classification: [examples/prompt-tuning-sst2.ipynb](./examples/prompt-tuning-sst2.ipynb) +- A personified chatbot: [examples/prompt-tuning-personachat.ipynb](./examples/prompt-tuning-personachat.ipynb) Here's a [more advanced tutorial](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm) that covers 8-bit quantization and best practices for running Petals.