update test-files

Signed-off-by: Mustafa <mustafa.cetin@intel.com>

Author: MSCetin37

CodeGen/tests/test_compose_on_gaudi.sh

@@ -60,7 +60,7 @@ function start_services() {
 
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
 
-    export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-32B-Instruct"
+    export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
     export LLM_ENDPOINT="http://${ip_address}:8028"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export MEGA_SERVICE_PORT=7778
@@ -144,8 +144,8 @@ function validate_microservices() {
         "completion_tokens" \
         "llm-service" \
         "${llm_container_name}" \
-        '{"model": "Qwen/Qwen2.5-Coder-32B-Instruct", "messages": [{"role": "user", "content": "def print_hello_world():"}], "max_tokens": 256}'
-
+        '{"model": "Qwen/Qwen2.5-Coder-7B-Instruct", "messages": [{"role": "user", "content": "def print_hello_world():"}], "max_tokens": 256}'
+        
     # llm microservice
     validate_services \
         "${ip_address}:9000/v1/chat/completions" \
@@ -176,7 +176,7 @@ function validate_megaservice() {
     # Curl the Mega Service with index_name and agents_flag
     validate_services \
         "${ip_address}:7778/v1/codegen" \
-        "completion_tokens" \
+        "" \
         "mega-codegen" \
         "codegen-gaudi-backend-server" \
         '{ "index_name": "test_redis", "agents_flag": "True", "messages": "def print_hello_world():", "max_tokens": 256}'

CodeGen/tests/test_compose_on_xeon.sh

@@ -62,7 +62,7 @@ function start_services() {
 
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
 
-    export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-32B-Instruct"
+    export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
     export LLM_ENDPOINT="http://${ip_address}:8028"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export MEGA_SERVICE_PORT=7778
@@ -143,7 +143,7 @@ function validate_microservices() {
         "completion_tokens" \
         "llm-service" \
         "${llm_container_name}" \
-        '{"model": "Qwen/Qwen2.5-Coder-32B-Instruct", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens": 256}'
+        '{"model": "Qwen/Qwen2.5-Coder-7B-Instruct", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens": 256}'
 
     # llm microservice
     validate_services \
@@ -175,7 +175,7 @@ function validate_megaservice() {
     # Curl the Mega Service with index_name and agents_flag
     validate_services \
         "${ip_address}:7778/v1/codegen" \
-        "completion_tokens" \
+        "" \
         "mega-codegen" \
         "codegen-xeon-backend-server" \
         '{ "index_name": "test_redis", "agents_flag": "True", "messages": "def print_hello_world():", "max_tokens": 256}'
@@ -255,7 +255,7 @@ function main() {
         sleep 5s
     done
 
-    echo y | docker system prune
+    # echo y | docker system prune
 }
 
 main