From a6890cbea9bb924ace978a35bc7d27d5cf5a7f56 Mon Sep 17 00:00:00 2001
From: drbh <david.richard.holtz@gmail.com>
Date: Fri, 26 Apr 2024 00:46:11 +0000
Subject: [PATCH] feat: update readme and container version

---
 README.md     | 12 ++++++++++++
 quickstart.sh |  2 +-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index ad66e328..8eaa6bd1 100644
--- a/README.md
+++ b/README.md
@@ -68,6 +68,18 @@ Text Generation Inference (TGI) is a toolkit for deploying and serving Large Lan
 
 ## Get Started
 
+### Quick Start ⚡️
+
+The fastest way to get started is to use the quickstart script. This script simplifies the docker and nvidia container toolkit installation process. It also installs the latest version of the text-generation-inference container and runs it with a default model.
+
+```bash
+curl --proto '=https' --tlsv1.2 -sSf \
+    https://raw.githubusercontent.com/huggingface/text-generation-inference/quickstart.sh \
+    | bash
+```
+![best practice script review](https://img.shields.io/badge/Best_Practice-yellow) Always review the contents of a script before running it.
+
+
 ### Docker
 
 For a detailed starting guide, please see the [Quick Tour](https://huggingface.co/docs/text-generation-inference/quicktour). The easiest way of getting started is using the official Docker container:
diff --git a/quickstart.sh b/quickstart.sh
index 42226488..eb8a88f6 100644
--- a/quickstart.sh
+++ b/quickstart.sh
@@ -35,4 +35,4 @@ model="HuggingFaceH4/zephyr-7b-beta"
 volume="$PWD/data"
 
 # Run the Docker container in interactive mode to allow CTRL+C to stop the container
-docker run -it --gpus all --shm-size 1g -p 8080:80 -v "$volume:/data" ghcr.io/huggingface/text-generation-inference:2.0 --model-id "$model"
+docker run -it --gpus all --shm-size 1g -p 8080:80 -v "$volume:/data" ghcr.io/huggingface/text-generation-inference:latest --model-id "$model"