Update app.py

app.py

@@ -4,24 +4,29 @@ import random
 
 API_URL = "https://api-inference.huggingface.co/models/"
 
-client = InferenceClient(
-    "mistralai/Mistral-7B-Instruct-v0.1"
-)
+# Initialize the InferenceClient
+client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
 
 def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
+    """Format the prompt for the text generation model."""
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
 
 def generate(prompt, history, temperature=0.9, max_new_tokens=512, top_p=0.95, repetition_penalty=1.0):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
+    """Generate a response using the text generation model."""
+    # Ensure temperature is not too low
+    temperature = max(float(temperature), 1e-2)
     top_p = float(top_p)
 
+    # Check if the prompt is asking who created the bot
+    if "who created you" in prompt.lower():
+        return "I was created by Aniket Kumar and many more."
+
+    # Set up parameters for text generation
     generate_kwargs = dict(
         temperature=temperature,
         max_new_tokens=max_new_tokens,
@@ -31,67 +36,72 @@ def generate(prompt, history, temperature=0.9, max_new_tokens=512, top_p=0.95, r
         seed=random.randint(0, 10**7),
     )
 
+    # Format the prompt
     formatted_prompt = format_prompt(prompt, history)
 
+    # Generate the response
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
-
     for response in stream:
         output += response.token.text
         yield output
     return output
 
+def create_interface():
+    """Create the Gradio interface."""
+    additional_inputs=[
+        gr.Slider(
+            label="Temperature",
+            value=0.9,
+            minimum=0.0,
+            maximum=1.0,
+            step=0.05,
+            interactive=True,
+            info="Higher values produce more diverse outputs",
+        ),
+        gr.Slider(
+            label="Max new tokens",
+            value=512,
+            minimum=64,
+            maximum=1024,
+            step=64,
+            interactive=True,
+            info="The maximum numbers of new tokens",
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            value=0.90,
+            minimum=0.0,
+            maximum=1,
+            step=0.05,
+            interactive=True,
+            info="Higher values sample more low-probability tokens",
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            value=1.2,
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            interactive=True,
+            info="Penalize repeated tokens",
+        )
+    ]
 
-additional_inputs=[
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Max new tokens",
-        value=512,
-        minimum=64,
-        maximum=1024,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=0.90,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1.2,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
-    )
-]
+    customCSS = """
+    #component-7 { # this is the default element ID of the chat component
+      height: 800px; # adjust the height as needed
+      flex-grow: 1;
+    }
+    """
 
-customCSS = """
-#component-7 { # this is the default element ID of the chat component
-  height: 800px; # adjust the height as needed
-  flex-grow: 1;
-}
-"""
+    with gr.Blocks(css=customCSS) as demo:
+        gr.ChatInterface(
+            generate,
+            additional_inputs=additional_inputs,
+        )
 
-with gr.Blocks(css=customCSS) as demo:
-    gr.ChatInterface(
-        generate,
-        additional_inputs=additional_inputs,
-    )
+    demo.queue().launch(debug=True)
 
-demo.queue().launch(debug=True)
+# Run the application
+create_interface()