From 1cd8033522e76aa81365415cf0cced61999438a5 Mon Sep 17 00:00:00 2001
From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Date: Tue, 23 May 2023 20:59:23 +0200
Subject: [PATCH] update readme

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 918ea5e2..30e085b2 100644
--- a/README.md
+++ b/README.md
@@ -81,7 +81,7 @@ model=bigscience/bloom-560m
 num_shard=2
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
-docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:latest --model-id $model --num-shard $num_shard
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.7 --model-id $model --num-shard $num_shard
 ```
 **Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher.