Update README.md

README.md

@@ -62,6 +62,28 @@ The following hyperparameters were used during training:
 ### Training results
 
 
+### How to use it?
+```
+from transformers import AutoTokenizer
+from transformers import TextGenerationPipeline, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("jed351/gpt2-tiny-zh-hk")
+model = AutoModelForCausalLM.from_pretrained("jed351/gpt2_tiny_zh-hk-shikoto")
+
+# try messing around with the parameters
+generator = TextGenerationPipeline(model, tokenizer, 
+                                   max_new_tokens=200, 
+                                   no_repeat_ngram_size=3, 
+                                   do_sample=True,
+                                   top_k=50, top_p=0.95, 
+                                   temperature=0.9) #, device=0) #if you have a GPU
+
+input_string = "已經返工"
+
+output = generator(input_string)
+string = output[0]['generated_text'].replace(' ', '')
+print(string)
+```
 
 ### Framework versions