Update app.py

app.py

@@ -25,7 +25,7 @@ class MessageRequest(BaseModel):
     message: str
     language: str
 
-repo_id = "HuggingFaceH4/zephyr-7b-alpha"
+repo_id = "openai-community/gpt2"
 llm_client = InferenceClient(
     model=repo_id,
     token=os.getenv("HF_TOKEN"),
@@ -61,8 +61,8 @@ templates = Jinja2Templates(directory="static")
 
 # Configure Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
-    model_name="HuggingFaceH4/zephyr-7b-alpha",
-    tokenizer_name="HuggingFaceH4/zephyr-7b-alpha",
+    model_name="openai-community/gpt2",
+    tokenizer_name="openai-community/gpt2",
     context_window=3000,
     token=os.getenv("HF_TOKEN"),
     max_new_tokens=512,