Update app.py

app.py

@@ -1,63 +1,65 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-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]})
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-    messages.append({"role": "user", "content": message})
+# Initialize model and tokenizer
+model = AutoModelForCausalLM.from_pretrained(
+    "microsoft/Phi-3.5-mini-instruct", 
+    device_map="cuda", 
+    torch_dtype="auto", 
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct")
 
-    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
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", 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)",
-        ),
-    ],
+# Create pipeline
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
 )
 
+# Generation arguments
+generation_args = {
+    "max_new_tokens": 1024,
+    "return_full_text": False,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+def chat(message, history, system_prompt):
+    # Prepare messages
+    messages = [
+        {"role": "system", "content": system_prompt},
+    ]
+    
+    # Add history to messages
+    for human, assistant in history:
+        messages.append({"role": "user", "content": human})
+        messages.append({"role": "assistant", "content": assistant})
+    
+    # Add current message
+    messages.append({"role": "user", "content": message})
+    
+    # Generate response
+    output = pipe(messages, **generation_args)
+    response = output[0]['generated_text']
+    
+    return response
+
+# Gradio interface
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.Button("Clear")
+    system_prompt = gr.Textbox(label="System Prompt", value="You are a helpful AI assistant.")
+
+    def respond(message, chat_history):
+        bot_message = chat(message, chat_history, system_prompt.value)
+        chat_history.append((message, bot_message))
+        return "", chat_history
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
 
 if __name__ == "__main__":
     demo.launch()