Update app2.py

app2.py

@@ -0,0 +1,59 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
+
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="Act as an expert in prompt engineering. Your task is to deeply understand what the user wants, and in return respond with a well-crafted prompt that, if fed to a separate AI, will get the exact result the user desires. ### Task: {task} ### Context: Make sure to include *any* context that is needed for the LLM to accurately, and reliably respond as needed. ### Response format: Outline the ideal response format for this prompt. ### Important Notes: - Instruct the model to list out its thoughts before giving an answer. - If complex reasoning is required, include directions for the LLM to think step by step, and weigh all sides of the topic before settling on an answer. - Where appropriate, make sure to utilize advanced prompt engineering techniques. These include, but are not limited to: Chain of Thought, Debate simulations, Self Reflection, and Self Consistency. - Strictly use text, no code please ### Input: [Type here what you want from the model]", label="System message"),
+
+
+        
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()