Spaces:
Runtime error
Runtime error
Create run.sh
Browse files
run.sh
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
git clone https://huggingface.co/Moses25/Mistral-7B-Instruct-32K-AWQ
|
| 3 |
+
python -m vllm.entrypoints.openai.api_server --model=Mistral-7B-Instruct-32K-AWQ \
|
| 4 |
+
--trust-remote-code --host 0.0.0.0 --port 7777 \
|
| 5 |
+
--gpu-memory-utilization 0.8 \
|
| 6 |
+
--enforce-eager \
|
| 7 |
+
--max-model-len 8192 --chat-template llama2-chat-template.jinja \
|
| 8 |
+
--tensor-parallel-size 1 --served-model-name dewu-chat
|