Update app.py

app.py

@@ -5,7 +5,7 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
 tokenizer  = AutoTokenizer.from_pretrained('humarin/chatgpt_paraphraser_on_T5_base', cache_dir='./Models')
 model = AutoModelForSeq2SeqLM.from_pretrained('humarin/chatgpt_paraphraser_on_T5_base', cache_dir='./Models')
-model = torch.quantization.quantize_dynamic(model, {torch.nn.Linear}, dtype=torch.qint8)
+model_quant = torch.quantization.quantize_dynamic(model, {torch.nn.Linear}, dtype=torch.qint8)
 
 def paraphrase(
     text,
@@ -25,7 +25,7 @@ def paraphrase(
         truncation=True,
     ).input_ids
     
-    outputs = model.generate(
+    outputs = model_quant.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,