Update app.py

app.py

@@ -1,35 +1,23 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-model_name = "microsoft/Phi-4-mini-instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32)
+# Загружаем модель
+model_id = "microsoft/Phi-4-mini-instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 
-def chat(user_input, history=[]):
-    messages = [{"role": "system", "content": "Ты полезный ассистент."}]
-    for i, (q, a) in enumerate(history):
-        messages.append({"role": "user", "content": q})
-        messages.append({"role": "assistant", "content": a})
-    messages.append({"role": "user", "content": user_input})
-    
-    inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
-    outputs = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.7)
-    reply = tokenizer.decode(outputs[0], skip_special_tokens=True).split("assistant")[-1].strip()
-    
-    history.append((user_input, reply))
-    return reply, history
+# Создаем пайплайн
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=200)
 
-with gr.Blocks() as demo:
-    gr.Markdown("# 🤖 Флэри чат (на Phi-4-mini)")
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox(label="Ваш вопрос")
-    state = gr.State([])
+# Функция генерации текста
+def chat(input_text):
+    result = pipe(input_text)[0]['generated_text']
+    return result
 
-    def respond(message, history):
-        reply, history = chat(message, history)
-        return chatbot.update(value=history), history
+# Интерфейс Gradio
+iface = gr.Interface(fn=chat, 
+                     inputs=gr.Textbox(lines=4, placeholder="Спроси меня что-нибудь..."), 
+                     outputs="text",
+                     title="💬 Chat с Phi-4-mini-instruct")
 
-    msg.submit(respond, [msg, state], [chatbot, state])
-
-demo.launch()
+iface.launch()