Update app.py

app.py

@@ -7,8 +7,10 @@ token = os.environ.get('HF_TOKEN')
 
 # Load model and tokenizer from Hugging Face
 model_name = "iqrabatool/finetuned_LLaMA"
-model = AutoModelForCausalLM.from_pretrained(model_name, token=os.environ.get('HF_TOKEN'))
-tokenizer = AutoTokenizer.from_pretrained(model_name, token=os.environ.get('HF_TOKEN'))
+
+# Define a smaller subset of the model or load a smaller version if available
+model = AutoModelForCausalLM.from_pretrained(model_name, token=token)
+tokenizer = AutoTokenizer.from_pretrained(model_name, token=token)
 
 def respond(message, system_message, max_tokens, temperature, top_p):
     # Generate response
@@ -17,21 +19,21 @@ def respond(message, system_message, max_tokens, temperature, top_p):
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response
 
-# Define interface components
+# Define simplified interface components
 additional_inputs = [
     gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-    gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-    gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-    gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+    gr.Slider(minimum=1, maximum=512, value=256, step=1, label="Max new tokens"),  # Limit max tokens
+    gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"),  # Reduce temperature range
+    gr.Slider(minimum=0.1, maximum=0.9, value=0.5, step=0.05, label="Top-p (nucleus sampling)"),  # Reduce top-p range
 ]
 
-# Create the ChatInterface
+# Create the simplified ChatInterface
 demo = gr.Interface(
     fn=respond,
     inputs=["text", "text", "number", "number", "number"],
     outputs="text",
     title="Health Bot",
-    description="A chatbot for health-related inquiries.",
+    description="A simplified chatbot for health-related inquiries.",
     article="The Health Bot assists users with health-related questions and provides information based on a pre-trained language model.",
     examples=[["What are the symptoms of COVID-19?", "Health Bot: COVID-19 symptoms include..."]],
     additional_inputs=additional_inputs