Create app.py

app.py

@@ -0,0 +1,56 @@
+from huggingface_hub import InferenceClient
+import gradio as gr
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-alpha")
+
+def format_prompt(message, history):
+  prompt = "<|system|>\n</s>\n"
+  for user_prompt, bot_response in history:
+    prompt += f"<|user|>\n {user_prompt} </s>\n"
+    prompt += f"<|assistant|>\n {bot_response} \n</s>\n "
+  prompt += f"<|user|>\n {message} </s>\n<|assistant|>"
+  return prompt
+
+def generate(
+    prompt, history, temperature=0.3, 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,
+    )
+
+    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
+
+
+mychatbot = gr.Chatbot(
+    bubble_full_width=False, show_label=False, show_copy_button=True,)
+
+
+with gr.Blocks() as demo:
+    gr.ChatInterface(
+        generate,
+        chatbot=mychatbot,
+        title="Z7 Chat",
+        retry_btn=None,
+        undo_btn=None,
+        clear_btn=None
+    )
+
+demo.queue(concurrency_count=30, max_size=100).launch(show_api=False)