From c9455730d743700ed5bba75eed0eb4d99de69abf Mon Sep 17 00:00:00 2001 From: fxmarty <9808326+fxmarty@users.noreply.github.com> Date: Fri, 17 May 2024 07:39:59 +0000 Subject: [PATCH] update version --- docs/source/basic_tutorials/gated_model_access.md | 2 +- docs/source/installation_amd.md | 2 +- docs/source/installation_nvidia.md | 2 +- docs/source/quicktour.md | 4 ++-- 4 files changed, 5 insertions(+), 5 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 $model ``` diff --git a/docs/source/installation_amd.md b/docs/source/installation_amd.md index 5111bab5..156f4e4b 100644 --- a/docs/source/installation_amd.md +++ b/docs/source/installation_amd.md @@ -11,7 +11,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading docker run --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \ --device=/dev/kfd --device=/dev/dri --group-add video \ --ipc=host --shm-size 256g --net host -v $volume:/data \ - ghcr.io/huggingface/text-generation-inference:1.4-rocm \ + ghcr.io/huggingface/text-generation-inference:2.0.3-rocm \ --model-id $model ``` diff --git a/docs/source/installation_nvidia.md b/docs/source/installation_nvidia.md index 9eb9fd4d..62e1a3d6 100644 --- a/docs/source/installation_nvidia.md +++ b/docs/source/installation_nvidia.md @@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run docker run --gpus all --shm-size 64g -p 8080:80 -v $volume:/data \ - ghcr.io/huggingface/text-generation-inference:1.4 \ + ghcr.io/huggingface/text-generation-inference:2.0.3 \ --model-id $model ``` diff --git a/docs/source/quicktour.md b/docs/source/quicktour.md index e1e8f200..6137c6f6 100644 --- a/docs/source/quicktour.md +++ b/docs/source/quicktour.md @@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B volume=$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 \ + ghcr.io/huggingface/text-generation-inference:2.0.3 \ --model-id $model ``` @@ -88,7 +88,7 @@ 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 ```