From 09c70a33b8804acaed5b01b6e9ecdd7b7bd67986 Mon Sep 17 00:00:00 2001 From: Jason Cox Date: Fri, 7 Jun 2024 23:04:56 -0700 Subject: [PATCH] Remove var in run example --- vllm/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/vllm/README.md b/vllm/README.md index 06b0273..02a5675 100644 --- a/vllm/README.md +++ b/vllm/README.md @@ -105,11 +105,10 @@ nvidia-docker run -d --gpus all -shm-size=10.24gb -p 8000:8000 \ -v $PWD/models:/root/.cache/huggingface \ --env "HF_TOKEN={Your_Hugingface_Token}" \ --restart unless-stopped \ - --name $CONTAINER \ + --name vllm \ vllm \ --host 0.0.0.0 \ --model=mistralai/Mistral-7B-Instruct-v0.1 \ - --served-model-name vllm \ --dtype=float \ --max-model-len 20000 @@ -120,6 +119,7 @@ nvidia-docker run -d --gpus all -shm-size=10.24gb -p 8000:8000 \ # --disable-log-requests # --tensor-parallel-size NUM_GPU # --enforce-eager + # --served-model-name mistral # Print Running Logs - ^C to Stop Viewing Logs docker logs vllm -f