Update default model cache for new CI cluster (opea-project#1445)

Signed-off-by: chensuyue <[email protected]>

Author: chensuyue

tests/llms/test_llms_doc-summarization_tgi_on_intel_hpu.sh

@@ -36,7 +36,7 @@ function start_service() {
     export MAX_INPUT_TOKENS=2048
     export MAX_TOTAL_TOKENS=4096
     export LOGFLAG=True
-    export DATA_PATH="/data2/cache"
+    export DATA_PATH="/data2/hf_model"
 
     cd $WORKPATH/comps/llms/deployment/docker_compose
     docker compose -f compose_doc-summarization.yaml up ${service_name} -d > ${LOG_PATH}/start_services_with_compose.log

tests/llms/test_llms_doc-summarization_vllm_on_intel_hpu.sh

@@ -51,7 +51,7 @@ function start_service() {
     export MAX_TOTAL_TOKENS=4096
     export VLLM_SKIP_WARMUP=true
     export LOGFLAG=True
-    export DATA_PATH="/data2/cache"
+    export DATA_PATH="/data2/hf_model"
 
     cd $WORKPATH/comps/llms/deployment/docker_compose
     docker compose -f compose_doc-summarization.yaml up ${service_name} -d > ${LOG_PATH}/start_services_with_compose.log

tests/llms/test_llms_faq-generation_tgi_on_intel_hpu.sh

@@ -34,7 +34,7 @@ function start_service() {
     export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
     export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
     export LOGFLAG=True
-    export DATA_PATH="/data2/cache"
+    export DATA_PATH="/data2/hf_model"
 
     cd $WORKPATH/comps/llms/deployment/docker_compose
     docker compose -f compose_faq-generation.yaml up ${service_name} -d > ${LOG_PATH}/start_services_with_compose.log

tests/llms/test_llms_faq-generation_vllm_on_intel_hpu.sh

@@ -50,7 +50,7 @@ function start_service() {
     export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
     export VLLM_SKIP_WARMUP=true
     export LOGFLAG=True
-    export DATA_PATH="/data2/cache"
+    export DATA_PATH="/data2/hf_model"
 
     cd $WORKPATH/comps/llms/deployment/docker_compose
     docker compose -f compose_faq-generation.yaml up ${service_name} -d > ${LOG_PATH}/start_services_with_compose.log

tests/llms/test_llms_text-generation_native_on_intel_hpu.sh

@@ -31,7 +31,7 @@ function start_service() {
     export host_ip=${host_ip}
     export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
     export LOGFLAG=True
-    export DATA_PATH="/data2/cache"
+    export DATA_PATH="/data2/hf_model"
 
     cd $WORKPATH/comps/llms/deployment/docker_compose
     docker compose -f compose_text-generation.yaml up ${service_name} -d > ${LOG_PATH}/start_services_with_compose.log

tests/llms/test_llms_text-generation_service_tgi_on_intel_hpu.sh

@@ -34,7 +34,7 @@ function start_service() {
     export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
     export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
     export LOGFLAG=True
-    export DATA_PATH="/data2/cache"
+    export DATA_PATH="/data2/hf_model"
 
     cd $WORKPATH/comps/llms/deployment/docker_compose
     docker compose -f compose_text-generation.yaml up ${service_name} -d > ${LOG_PATH}/start_services_with_compose.log

tests/llms/test_llms_text-generation_service_vllm_on_intel_hpu.sh

@@ -49,7 +49,7 @@ function start_service() {
     export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
     export VLLM_SKIP_WARMUP=true
     export LOGFLAG=True
-    export DATA_PATH="/data2/cache"
+    export DATA_PATH="/data2/hf_model"
 
     cd $WORKPATH/comps/llms/deployment/docker_compose
     docker compose -f compose_text-generation.yaml up ${service_name} -d > ${LOG_PATH}/start_services_with_compose.log

tests/retrievers/test_retrievers_neo4j_on_intel_hpu.sh

@@ -43,7 +43,7 @@ function start_service() {
     export LLM_ENDPOINT_PORT=11634
     export RETRIEVER_PORT=11635
     export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export DATA_PATH="/data2/cache"
+    export DATA_PATH="/data2/hf_model"
     export MAX_INPUT_TOKENS=4096
     export MAX_TOTAL_TOKENS=8192
     export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:${TEI_EMBEDDER_PORT}"