Update app.py

app.py

@@ -1,22 +1,18 @@
-from huggingface_hub import InferenceClient
+from huggingface_hub import InferenceAPI
+from urllib.parse import urlparse, parse_qs
 import gradio as gr
 
-client = InferenceClient(
-    "mistralai/Mistral-7B-Instruct-v0.1"
-)
-
+api = InferenceAPI("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
-
-def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
+    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=256, top_p=0.95, repetition_penalty=1.0):
     temperature = float(temperature)
     if temperature < 1e-2:
         temperature = 1e-2
@@ -32,59 +28,28 @@ def generate(
     )
 
     formatted_prompt = format_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.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=256,
-        minimum=0,
-        maximum=1048,
-        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",
-    )
-]
-
-
-gr.ChatInterface(
-    fn=generate,
-    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
-    additional_inputs=additional_inputs,
-    title="""Mistral 7B 01"""
-).launch(show_api=True)
+    response = api.generate_text(formatted_prompt, **generate_kwargs)
+    return response
+
+def chatbot(message):
+    history = []
+    response = generate(message, history)
+    history.append(("User", message))
+    history.append(("ChatBot", response))
+    return response
+
+def get_message_from_url():
+    url = urlparse(gradio.Interface.get_share_url())
+    query_params = parse_qs(url.query)
+    if "message" in query_params:
+        return query_params["message"][0]
+    return ""
+
+message = get_message_from_url()
+inputs = gr.inputs.Textbox(lines=2, placeholder="Type your message here...", initial_message=message)
+outputs = gr.outputs.Textbox()
+
+title = "Mistral 7B Chatbot"
+description = "Chat with Mistral 7B, a powerful language model!"
+
+gr.Interface(fn=chatbot, inputs=inputs, outputs=outputs, title=title, description=description).launch()