Update app.py

app.py

@@ -1,34 +1,30 @@
 
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 import gradio as gr
 
-# Загружаем модель rut5-base с медленным токенизатором
-model_name = "cointegrated/rut5-base"
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
-model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+model_name = "sberbank-ai/rugpt3medium_based_on_gpt2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
-# Функция генерации ответа
 def generate_response(prompt):
-    input_ids = tokenizer.encode(prompt, return_tensors="pt", max_length=512, truncation=True)
-    with torch.no_grad():
-        output_ids = model.generate(
-            input_ids,
-            max_length=200,
-            num_beams=5,
-            do_sample=True,
-            top_p=0.9,
-            temperature=0.8,
-            pad_token_id=tokenizer.pad_token_id,
-            eos_token_id=tokenizer.eos_token_id
-        )
-    response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    input_ids = tokenizer.encode(prompt, return_tensors="pt")
+    output = model.generate(
+        input_ids,
+        max_length=200,
+        num_return_sequences=1,
+        do_sample=True,
+        top_k=50,
+        top_p=0.95,
+        temperature=0.9,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
     return response
 
-# Gradio-интерфейс
 iface = gr.Interface(
     fn=generate_response,
-    inputs=gr.Textbox(lines=4, label="Введите ваш запрос"),
+    inputs=gr.Textbox(label="Введите ваш вопрос"),
     outputs=gr.Textbox(label="Ответ модели"),
     title="Интерфейс ChatGPT",
     description="Пример взаимодействия с API OpenAI через Hugging Face Space"