From fc127312dfcafab371e4ff3c3a31d955cf1d90fb Mon Sep 17 00:00:00 2001
From: fxmarty <9808326+fxmarty@users.noreply.github.com>
Date: Fri, 17 May 2024 07:35:43 +0000
Subject: [PATCH] update tgi version

---
 docs/source/basic_tutorials/gated_model_access.md | 2 +-
 docs/source/quicktour.md                          | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/docs/source/basic_tutorials/gated_model_access.md b/docs/source/basic_tutorials/gated_model_access.md
index 060d177d..970afa0e 100644
--- a/docs/source/basic_tutorials/gated_model_access.md
+++ b/docs/source/basic_tutorials/gated_model_access.md
@@ -19,6 +19,6 @@ 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:1.4 \
+    -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.0.3 \
     --model-id $model
 ```
diff --git a/docs/source/quicktour.md b/docs/source/quicktour.md
index 70cf575c..6e055de1 100644
--- a/docs/source/quicktour.md
+++ b/docs/source/quicktour.md
@@ -8,7 +8,7 @@ Let's say you want to deploy [teknium/OpenHermes-2.5-Mistral-7B](https://hugging
 model=teknium/OpenHermes-2.5-Mistral-7B
 volume=$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:1.4 --model-id $model
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.0.3 --model-id $model
 ```
 
 <Tip warning={true}>
@@ -20,7 +20,7 @@ To use NVIDIA GPUs, you need to install the [NVIDIA Container Toolkit](https://d
 TGI also supports ROCm-enabled AMD GPUs (only MI210 and MI250 are tested), details are available in the [Supported Hardware section](./supported_models#supported-hardware) and [AMD documentation](https://rocm.docs.amd.com/en/latest/deploy/docker.html). To launch TGI on ROCm GPUs, please use instead:
 
 ```bash
-docker run --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.4-rocm --model-id $model
+docker run --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.0.3-rocm --model-id $model
 ```
 
 Once TGI is running, you can use the `generate` endpoint by doing requests. To learn more about how to query the endpoints, check the [Consuming TGI](./basic_tutorials/consuming_tgi) section, where we show examples with utility libraries and UIs. Below you can see a simple snippet to query the endpoint.
@@ -91,7 +91,7 @@ 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:1.4 --help
+docker run ghcr.io/huggingface/text-generation-inference:2.0.3 --help
 ```
 
 </Tip>