Update README.md

README.md

@@ -15,5 +15,35 @@ widget:
 
 中文版对话机器人
 
+在1000w+问答和对话数据上做有监督预训练
 
-在1000w+问答和对话数据上做有监督预训练
+请使用下面方式调用模型输出结果，Hosted inference API的结果因为我无法修改后台推理程序，不能保证模型输出效果，只是举了两个例子展示展示。
+
+Install package:
+```
+pip install transformers 
+```
+
+```python
+import os
+os.environ["CUDA_VISIBLE_DEVICES"] = '-1'
+import torch
+from torch import cuda
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+tokenizer = AutoTokenizer.from_pretrained("mxmax/Chinese_Chat_T5_Base")
+model = AutoModelForSeq2SeqLM.from_pretrained("mxmax/Chinese_Chat_T5_Base") 
+device = 'cuda' if cuda.is_available() else 'cpu'
+model_trained.to(device)
+def postprocess(text):
+  return text.replace(".", "").replace('</>','')
+
+def answer_fn(text, sample=False, top_p=0.6):
+  encoding = tokenizer(text=[text], truncation=True, padding=True, max_length=256, return_tensors="pt").to(device) 
+  out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_length=512,temperature=0.5,do_sample=True,repetition_penalty=6.0 ,top_p=top_p)
+  result = tokenizer.batch_decode(out["sequences"], skip_special_tokens=True)
+  return postprocess(result[0]) 
+text="宫颈癌的早期会有哪些危险信号"
+result=answer_fn(text, sample=True, top_p=0.6)
+print('prompt:',text)
+print("result:",result)
+```