Spaces:

Moses25
/

Mistral-7B-Instruct-32K-AWQ-chatbot

Runtime error

Moses25 commited on Jun 5

Commit

2b10985

•

1 Parent(s): 46485d7

Update run.sh

Files changed (1) hide show

run.sh CHANGED Viewed

@@ -8,7 +8,7 @@ git clone https://github.com/vllm-project/vllm.git
 cd vllm && VLLM_TARGET_DEVICE=cpu python setup.py install && cd ..
 git clone https://huggingface.co/Moses25/Mistral-7B-Instruct-32K-AWQ
-set VLLM_CPU_KVCACHE_SPACE=15
 python  -m vllm.entrypoints.openai.api_server --model=Mistral-7B-Instruct-32K-AWQ \
         --trust-remote-code --host 0.0.0.0  --port 7777 \
         --gpu-memory-utilization 0.8 \

 cd vllm && VLLM_TARGET_DEVICE=cpu python setup.py install && cd ..
 git clone https://huggingface.co/Moses25/Mistral-7B-Instruct-32K-AWQ
+eexport VLLM_CPU_KVCACHE_SPACE=15
 python  -m vllm.entrypoints.openai.api_server --model=Mistral-7B-Instruct-32K-AWQ \
         --trust-remote-code --host 0.0.0.0  --port 7777 \
         --gpu-memory-utilization 0.8 \