Update app.py

app.py

@@ -153,7 +153,7 @@ def readitaloud(result):
 
 def chat_with_model(prompt, document_section, model_choice='Llama-2-7b-chat-hf'):
     # API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud'  # Dr Llama
-    API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"  # HF default model for l7b
+    API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"  # HF model for Llama 7B
     #API_KEY = os.getenv('API_KEY')
     API_KEY = os.getenv('HF_KEY')
     MODEL1="meta-llama/Llama-2-7b-chat-hf"
@@ -170,6 +170,7 @@ def chat_with_model(prompt, document_section, model_choice='Llama-2-7b-chat-hf')
     if len(document_section)>0:
         conversation.append({'role': 'assistant', 'content': document_section})
     start_time = time.time()
+    st.write('starting at ', start_time)
     report = []
     res_box = st.empty()
     collected_chunks = []