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>
2024-08-30 13:54:42 +08:00
parent d487093d10
commit f5f1e323bb
3 changed files with 3 additions and 3 deletions
--- 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