updated to use my model

app.py

@@ -19,7 +19,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "32768"))
 
 if torch.cuda.is_available():
-    model_id = "cyberagent/calm2-7b-chat"
+    model_id = "vericava/llm-jp-3-1.8b-instruct-lora-vericava7"
     my_pipeline=pipeline(
         model=model_id,
     )