Create app.py

app.py

@@ -0,0 +1,51 @@
+from huggingface_hub import InferenceClient
+import gradio as gr
+
+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
+
+def generate(
+    prompt, history, system_prompt, 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
+    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,
+    )
+
+    system_prompt = "You are Mixtral, a gentle and smart AI assistant who is always ready to help and answer any questions truthfully"
+
+    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
+
+mychatbot = gr.Chatbot(
+    avatar_images=["./user.png", "./bot.png"], bubble_full_width=False, show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel")
+
+gr.ChatInterface(
+    fn=generate,
+    chatbot=mychatbot,
+    title="Tomoniai's Mixtral Chat",
+    retry_btn=None,
+    undo_btn=None
+).launch(show_api=False)