large model

app.py

@@ -19,26 +19,27 @@ model = T5ForConditionalGeneration.from_pretrained("ClueAI/ChatYuan-large-v1")
 
 device = torch.device('cpu')
 model.to(device)
-def preprocess(text):
-  return text.replace("\n", "_")
 
+def preprocess(text):
+  text = text.replace("\n", "\\n").replace("\t", "\\t")
+  return text
+ 
 def postprocess(text):
-  return text.replace("_", "\n")
-
-def answer(text, sample=False, top_p=0.6):
+  return text.replace("\\n", "\n").replace("\\t", "\t")
+ 
+def answer(text, sample=True, top_p=1, temperature=0.7):
   '''sample：是否抽样。生成任务，可以设置为True;
   top_p：0-1之间，生成的内容越多样'''
   text = preprocess(text)
   encoding = tokenizer(text=[text], truncation=True, padding=True, max_length=768, return_tensors="pt").to(device) 
   if not sample:
-    out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_new_tokens=128, num_beams=4, length_penalty=0.6)
+    out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_new_tokens=512, num_beams=1, length_penalty=0.6)
   else:
-    out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_new_tokens=128, do_sample=True, top_p=top_p)
+    out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_new_tokens=512, do_sample=True, top_p=top_p, temperature=temperature, no_repeat_ngram_size=3)
   out_text = tokenizer.batch_decode(out["sequences"], skip_special_tokens=True)
   return postprocess(out_text[0])
 
 
-
 #iface = gr.Interface(fn=answer, inputs="text", outputs="text")
 examples = [
     ["""摘要这段话: