Update README.md

README.md

@@ -40,3 +40,38 @@ The typed schema is :
 schema = ['事件', '自然科学', '建筑结构', '地理地区', '组织', '医学', '天文对象', '人造物件', '运输', '作品', '生物', '人物']
 ```
 
+Try the following case:
+
+```python
+cat_char = '🐱'
+bot_char = '🤖'
+instruction ='你是一个图谱实体知识结构化专家。请从input中抽取出符合schema定义的实体实例和其属性，不存在的属性不输出，属性存在多值就返回列表。请按照JSON字符串的格式回答。'
+schema = schemas['人物']
+input_text = "个人简介姓名：拉塞·维比  所属球队：布伦特福德  国籍：丹麦、法国、荷兰、法属圭亚那  出生日期：1987-02-22  身高：181cm  体重：73kg  场上位置：前锋  球衣号码：21  丹麦射手拉塞-维比，获得了2014赛季瑞超联赛金靴"
+input_text = {'input': input_text, 'schema': schema}
+input_text = json.dumps(input_text).decode('UTF-8')
+ctx = f'{cat_char}:{instruction}\n{input_text}\n{bot_char}:'
+print(ctx)
+
+def my_print(s):
+    print(s, end='', flush=True)
+
+# For alpha_frequency and alpha_presence, see "Frequency and presence penalties":
+# https://platform.openai.com/docs/api-reference/parameter-details
+
+args = PIPELINE_ARGS(temperature = 1.0, top_p = 0, top_k = 0, # top_k = 0 then ignore
+                     alpha_frequency = 0.25,
+                     alpha_presence = 0.25,
+                     alpha_decay = 0.996, # gradually decay the penalty
+                     token_ban = [0], # ban the generation of some tokens
+                     token_stop = [0,1], # stop generation whenever you see any token here
+                     chunk_len = 256) # split input into chunks to save VRAM (shorter -> slower)
+
+pipeline.generate(ctx, token_count=200, args=args, callback=my_print,state=states_value)
+print('\n')
+```
+
+The output should look like:
+```bash
+{"result":人物}
+```