Revert the LLM model for kubernetes GMS (#675)

* revert the LLM model to meta-llama/CodeLlama-7b-hf Signed-off-by: zhlsunshine <huailong.zhang@intel.com>
opea-project · Aug 30, 2024 · f5f1e32 · f5f1e32
1 parent d487093
commit f5f1e32
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/CodeGen/kubernetes/codegen_xeon.yaml b/CodeGen/kubernetes/codegen_xeon.yaml
@@ -29,6 +29,6 @@ spec:
  internalService:
  serviceName: tgi-service
  config:
- MODEL_ID: HuggingFaceH4/mistral-7b-grok
+ MODEL_ID: meta-llama/CodeLlama-7b-hf
  endpoint: /generate
  isDownstreamService: true
diff --git a/CodeGen/tests/test_gmc_on_gaudi.sh b/CodeGen/tests/test_gmc_on_gaudi.sh
@@ -34,7 +34,7 @@ function validate_codegen() {
  export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
  echo "$CLIENT_POD"
  accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='codegen')].status.accessUrl}")
- kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -X POST -d '{"query": "def print_hello_world():"}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_codegen.log
+ kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -X POST -d '{"inputs":"Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception.","parameters":{"max_new_tokens":256, "do_sample": true}}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_codegen.log
  exit_code=$?
  if [ $exit_code -ne 0 ]; then
  echo "chatqna failed, please check the logs in ${LOG_PATH}!"

diff --git a/CodeGen/tests/test_gmc_on_xeon.sh b/CodeGen/tests/test_gmc_on_xeon.sh
@@ -34,7 +34,7 @@ function validate_codegen() {
  export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
  echo "$CLIENT_POD"
  accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='codegen')].status.accessUrl}")
- kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -X POST -d '{"query": "def print_hello_world():"}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_codegen.log
+ kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -X POST -d '{"inputs":"Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception.","parameters":{"max_new_tokens":256, "do_sample": true}}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_codegen.log
  exit_code=$?
  if [ $exit_code -ne 0 ]; then
  echo "chatqna failed, please check the logs in ${LOG_PATH}!"