From bd1bdebb47472f0947171c5c2e36b3daa593d2e7 Mon Sep 17 00:00:00 2001
From: David Corvoysier <david@huggingface.co>
Date: Wed, 18 Jun 2025 12:35:36 +0200
Subject: [PATCH] doc: fix README (#3271)

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 3c385b83..b2e818a1 100644
--- a/README.md
+++ b/README.md
@@ -84,7 +84,7 @@ model=HuggingFaceH4/zephyr-7b-beta
 volume=$PWD/data
 
 docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:3.3.2 --model-id $model
+    ghcr.io/huggingface/text-generation-inference:3.3.3 --model-id $model
 ```
 
 And then you can make requests like
@@ -152,7 +152,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 token=<your cli READ token>
 
 docker run --gpus all --shm-size 1g -e HF_TOKEN=$token -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:3.3.2 --model-id $model
+    ghcr.io/huggingface/text-generation-inference:3.3.3 --model-id $model
 ```
 
 ### A note on Shared Memory (shm)