Update app.py

app.py

@@ -5,49 +5,54 @@ from huggingface_hub import InferenceClient
 client = InferenceClient("mistralai/Mixtral-8x7B-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
+  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, system_prompt, temperature=0.9, max_new_tokens=9048, top_p=0.95, repetition_penalty=1.0):
-    temperature = max(float(temperature), 1e-2)
-    top_p = float(top_p)
-
-    generate_kwargs = dict(
-        temperature=temperature,
-        max_new_tokens=max_new_tokens,
-        top_p=top_p,
-        repetition_penalty=repetition_penalty,
-        do_sample=True,
-        seed=42,
-    )
-
-    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
-    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
-
-additional_inputs = [
-    gr.Textbox(label="System Prompt", max_lines=1, interactive=True),
-    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=9048, minimum=256, maximum=9048, 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")
-]
-
+  temperature = max(float(temperature), 1e-2)
+  top_p = float(top_p)
+
+  generate_kwargs = dict(
+      temperature=temperature,
+      max_new_tokens=max_new_tokens,
+      top_p=top_p,
+      repetition_penalty=repetition_penalty,
+      do_sample=True,
+      seed=42,
+  )
+
+  formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
+  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
+
+# Define inputs (user interface elements)
+system_prompt_input = gr.Textbox(label="System Prompt", max_lines=1, interactive=True)
+slider_temperature = 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")
+slider_max_tokens = gr.Slider(label="Max new tokens", value=9048, minimum=256, maximum=9048, step=64, interactive=True, info="The maximum numbers of new tokens")
+slider_top_p = 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")
+slider_repetition_penalty = gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens")
+inputs = [system_prompt_input] + [slider_temperature, slider_max_tokens, slider_top_p, slider_repetition_penalty]
+
+# Define output (generated text)
+output_text = gr.Textbox(label="Output")
+
+# Create the Gradio interface
 gr.Interface(
-    fn=generate,
-    chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True, likeable=True, layout="panel"),
-    additional_inputs=additional_inputs,
-    title="ConvoLite",
-    description="Remember! The AI might give incorrect information about people, locations, history, etc...",
-    concurrency_limit=20,
-    theme=gr.themes.Soft()  # Set the theme here
+  fn=generate,
+  chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True, likeable=True, layout="panel"),
+  inputs=inputs,
+  outputs=output_text,
+  title="ConvoLite",
+  description="Remember! The AI might give incorrect information about people, locations, history, etc...",
+  concurrency_limit=20,
+  theme=gr.themes.Soft()
 ).launch(show_api=False,)