From 7a6fad6aac67d9bf21fe75c034a6bcab5dbd88d2 Mon Sep 17 00:00:00 2001
From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Date: Thu, 28 Sep 2023 10:18:18 +0200
Subject: [PATCH] update readme

---
 README.md                | 2 +-
 docs/source/quicktour.md | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index c6db2822..339b5db7 100644
--- a/README.md
+++ b/README.md
@@ -155,7 +155,7 @@ model=meta-llama/Llama-2-7b-chat-hf
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 token=<your cli READ token>
 
-docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.3 --model-id $model
+docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.1.0 --model-id $model
 ```
 
 ### A note on Shared Memory (shm)
diff --git a/docs/source/quicktour.md b/docs/source/quicktour.md
index 083dffa5..0a874b57 100644
--- a/docs/source/quicktour.md
+++ b/docs/source/quicktour.md
@@ -85,7 +85,7 @@ curl 127.0.0.1:8080/generate \
 To see all possible deploy flags and options, you can use the `--help` flag. It's possible to configure the number of shards, quantization, generation parameters, and more.
 
 ```bash
-docker run ghcr.io/huggingface/text-generation-inference:1.0.3 --help
+docker run ghcr.io/huggingface/text-generation-inference:1.1.0 --help
 ```
 
 </Tip>