Update README.md

README.md

@@ -25,24 +25,23 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2-shikoto
 
-This model is a fine-tuned version of [jed351/gpt2-tiny-zh-hk](https://huggingface.co/jed351/gpt2-tiny-zh-hk) on the jed351/shikoto_zh_hk dataset.
-It achieves the following results on the evaluation set:
-- Loss: 3.2965
-- Accuracy: 0.3738
+This model was trained on a dataset I obtained from an online novel site. 
+**Please be aware that the stories might contain inappropriate content**
 
-## Model description
 
-More information needed
+The base model can be found [here](https://huggingface.co/jed351/gpt2-tiny-zh-hk), which was obtained from 
+patching a GPT2 Chinese model and its tokenizer with Cantonese characters. 
 
-## Intended uses & limitations
 
-More information needed
 
-## Training and evaluation data
+## Training procedure
 
-More information needed
+Please refer to the [script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/language-modeling) 
+provided by Huggingface. 
+
+
+The model was trained for 400,000 steps on 2 NVIDIA Quadro RTX6000 for around 15 hours.
 
-## Training procedure
 
 ### Training hyperparameters