Update README.md

README.md

@@ -20,20 +20,30 @@ Wenzhong-GPT2-110M is one of the Wenzhong series, which has smaller parameters.
 
 ### load model
 ```python 
-from transformers import GPT2Tokenizer, GPT2Model
-tokenizer = GPT2Tokenizer.from_pretrained('IDEA-CCNL/Wenzhong-GPT2-3.5B')
-model = GPT2Model.from_pretrained('IDEA-CCNL/Wenzhong-GPT2-3.5B')
-text = "Replace me by any text you'd like."
-encoded_input = tokenizer(text, return_tensors='pt')
-output = model(**encoded_input)
-```
+from transformers import GPT2Tokenizer,GPT2LMHeadModel
+hf_model_path = 'IDEA-CCNL/Wenzhong-GPT2-110M'
+tokenizer = GPT2Tokenizer.from_pretrained(hf_model_path)
+model = GPT2LMHeadModel.from_pretrained(hf_model_path)```
 ### generation
 ```python
-from transformers import pipeline, set_seed
-set_seed(55)
-generator = pipeline('text-generation', model='IDEA-CCNL/Wenzhong-GPT2-3.5B')
-generator("北京位于", max_length=30, num_return_sequences=1)
+question = "北京是中国的"
+inputs = tokenizer(question,return_tensors='pt')
+generation_output = model.generate(**inputs,
+                                return_dict_in_generate=True,
+                                output_scores=True,
+                                max_length=150,
+                                # max_new_tokens=80,
+                                do_sample=True,
+                                top_p = 0.6,
+                                # num_beams=5,
+                                eos_token_id=50256,
+                                pad_token_id=0,
+                                # stopping_criteria = StoppingCriteriaList([custom_stopping(stop_token=50256)]),
+                                num_return_sequences = 5)
 
+for idx,sentence in enumerate(generation_output.sequences):
+    print('next sentence %d:\n'%idx,tokenizer.decode(sentence).split('<|endoftext|>')[0])
+    print('*'*40)
 ```
 
 ## Citation