Update app.py

app.py

@@ -1,16 +1,48 @@
 import gradio as gr
-from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+device = "cpu"
 
-pipe = pipeline("text2text-generation", model="humarin/chatgpt_paraphraser_on_T5_base")
+tokenizer = AutoTokenizer.from_pretrained("humarin/chatgpt_paraphraser_on_T5_base")
+
+model = AutoModelForSeq2SeqLM.from_pretrained("humarin/chatgpt_paraphraser_on_T5_base").to(device)
+
+def paraphrase(
+    question,
+    num_beams=5,
+    num_beam_groups=5,
+    num_return_sequences=1,
+    repetition_penalty=10.0,
+    diversity_penalty=3.0,
+    no_repeat_ngram_size=2,
+    temperature=0.7,
+    max_length=128
+):
+    input_ids = tokenizer(
+        f'paraphrase: {question}',
+        return_tensors="pt", padding="longest",
+        max_length=max_length,
+        truncation=True,
+    ).input_ids.to(device)
+    
+    outputs = model.generate(
+        input_ids, temperature=temperature, repetition_penalty=repetition_penalty,
+        num_return_sequences=num_return_sequences, no_repeat_ngram_size=no_repeat_ngram_size,
+        num_beams=num_beams, num_beam_groups=num_beam_groups,
+        max_length=max_length, diversity_penalty=diversity_penalty
+    )
+
+    res = tokenizer.batch_decode(outputs, skip_special_tokens=True)
+
+    return res
 
 
 def launch(input):
-    out = pipe(input)
+    out = paraphrase(input)
     return out[0]['generated_text']
 
 iface = gr.Interface(launch,
                      inputs="textbox",
-                     outputs="text")
+                     outputs="textbox")
 
 iface.launch()