From 11fced79bdffefff59fd019423cbb72cf63541aa Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Thu, 27 Jun 2024 12:34:43 +0200 Subject: [PATCH] Bumping to 2.1 (#2131) --- docs/source/installation_amd.md | 2 +- docs/source/installation_nvidia.md | 2 +- docs/source/quicktour.md | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/source/installation_amd.md b/docs/source/installation_amd.md index bf7f9c751..fe925e2a3 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:2.0.4-rocm \ + ghcr.io/huggingface/text-generation-inference:2.1.0-rocm \ --model-id $model ``` diff --git a/docs/source/installation_nvidia.md b/docs/source/installation_nvidia.md index 9077f7fd9..11c417634 100644 --- a/docs/source/installation_nvidia.md +++ b/docs/source/installation_nvidia.md @@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B volume=$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:2.0.4 \ + ghcr.io/huggingface/text-generation-inference:2.1.0 \ --model-id $model ``` diff --git a/docs/source/quicktour.md b/docs/source/quicktour.md index b84de85d5..09e56df47 100644 --- a/docs/source/quicktour.md +++ b/docs/source/quicktour.md @@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B volume=$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:2.0.4 \ + ghcr.io/huggingface/text-generation-inference:2.1.0 \ --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:2.0.4 --help +docker run ghcr.io/huggingface/text-generation-inference:2.1.0 --help ```