Spaces:
Running
on
A100
Running
on
A100
Update entrypoint.sh.template
Browse files- entrypoint.sh.template +1 -2
entrypoint.sh.template
CHANGED
@@ -4,8 +4,7 @@
|
|
4 |
mongod &
|
5 |
|
6 |
# Start the text-generation-inference process
|
7 |
-
text-generation-launcher --model-id ${MODEL_NAME} --num-shard 1 --port 8080 --trust-remote-code
|
8 |
-
text-generation-launcher --model-id HuggingFaceH4/starcoder2-15b-dpo-v40-deploy --num-shard 1 --port 8081 --trust-remote-code --shard-uds-path /tmp/text-generation-model-b --master-port 25001 --cuda-memory-fraction 0.5 &
|
9 |
|
10 |
# Wait for text-generation-inference to start
|
11 |
curl --retry 60 --retry-delay 10 --retry-connrefused http://127.0.0.1:8080/health
|
|
|
4 |
mongod &
|
5 |
|
6 |
# Start the text-generation-inference process
|
7 |
+
text-generation-launcher --model-id ${MODEL_NAME} --num-shard 1 --port 8080 --trust-remote-code &
|
|
|
8 |
|
9 |
# Wait for text-generation-inference to start
|
10 |
curl --retry 60 --retry-delay 10 --retry-connrefused http://127.0.0.1:8080/health
|