fixed bug in test.py

.env.example

@@ -19,7 +19,7 @@ HF_PIPELINE_DEVICE_TYPE=
 # LOAD_QUANTIZED_MODEL=4bit
 # LOAD_QUANTIZED_MODEL=8bit
 
-DISABLE_MODEL_PRELOADING=false
+DISABLE_MODEL_PRELOADING=true
 CHAT_HISTORY_ENABLED=true
 SHOW_PARAM_SETTINGS=false
 SHARE_GRADIO_APP=false

data/questions.txt

@@ -1,3 +1,4 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5f61185685e79b9b115f1b3d34c6bca2913174a18c014b210e749e419beb2211
-size 60
+What's AI?
+life in AI era
+machine learning
+generative model

test.py

@@ -128,7 +128,7 @@ while True:
     custom_handler.reset()
 
     start = timer()
-    result = qa_chain.call({"question": query, "chat_history": chat_history})
+    result = qa_chain.call({"question": query, "chat_history": chat_history}, None)
     end = timer()
     print(f"Completed in {end - start:.3f}s")