jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

Revert the LLM model for kubernetes GMS (#675)

Browse Source 
* revert the LLM model to meta-llama/CodeLlama-7b-hf
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>
This commit is contained in:
Steve Zhang
2024-08-30 13:54:42 +08:00
committed by GitHub
parent d487093d10
commit f5f1e323bb
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CodeGen/kubernetes/codegen_xeon.yaml
View File

@@ -29,6 +29,6 @@ spec:
internalService: internalService:
serviceName: tgi-service serviceName: tgi-service
config: config:
MODEL_ID: HuggingFaceH4/mistral-7b-grok MODEL_ID: meta-llama/CodeLlama-7b-hf
endpoint: /generate endpoint: /generate
isDownstreamService: true isDownstreamService: true

2
CodeGen/tests/test_gmc_on_gaudi.sh
View File

@@ -34,7 +34,7 @@ function validate_codegen() {
export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name}) export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
echo "$CLIENT_POD" echo "$CLIENT_POD"
accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='codegen')].status.accessUrl}") accessUrl=$(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' > $LOG_PATH/gmc_codegen.log
exit_code=$? exit_code=$?
if [ $exit_code -ne 0 ]; then if [ $exit_code -ne 0 ]; then
echo "chatqna failed, please check the logs in ${LOG_PATH}!" echo "chatqna failed, please check the logs in ${LOG_PATH}!"

2
CodeGen/tests/test_gmc_on_xeon.sh
View File

@@ -34,7 +34,7 @@ function validate_codegen() {
export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name}) export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
echo "$CLIENT_POD" echo "$CLIENT_POD"
accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='codegen')].status.accessUrl}") accessUrl=$(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' > $LOG_PATH/gmc_codegen.log
exit_code=$? exit_code=$?
if [ $exit_code -ne 0 ]; then if [ $exit_code -ne 0 ]; then
echo "chatqna failed, please check the logs in ${LOG_PATH}!" echo "chatqna failed, please check the logs in ${LOG_PATH}!"