Update README.md

README.md

@@ -78,7 +78,7 @@ distilled_student_sentiment_classifier("私はこの映画が大好きで、何
 
 ## Training procedure
 
-Notebook link: TBU
+Notebook link: [here](https://github.com/LxYuan0420/nlp/blob/main/notebooks/Distilling_Zero_Shot_multilingual_distilbert_sentiments_student.ipynb)
 
 ### Training hyperparameters
 
@@ -99,19 +99,19 @@ python transformers/examples/research_projects/zero-shot-distillation/distill_cl
 
 If you are training this model on Colab, make the following code changes to avoid Out-of-memory error message:
 ```bash
-  ###### modify L78 to disable fast tokenizer 
-  default=False,
+###### modify L78 to disable fast tokenizer 
+default=False,
 
-  ###### update dataset map part at L313
-  dataset = dataset.map(tokenizer, input_columns="text", fn_kwargs={"padding": "max_length", "truncation": True, "max_length": 512})
+###### update dataset map part at L313
+dataset = dataset.map(tokenizer, input_columns="text", fn_kwargs={"padding": "max_length", "truncation": True, "max_length": 512})
 
-  ###### add following lines to L213
-  del model
-  print(f"Manually deleted Teacher model, free some memory for student model.")
+###### add following lines to L213
+del model
+print(f"Manually deleted Teacher model, free some memory for student model.")
 
-  ###### add following lines to L337
-  trainer.push_to_hub()
-  tokenizer.push_to_hub("distilbert-base-multilingual-cased-sentiments-student")
+###### add following lines to L337
+trainer.push_to_hub()
+tokenizer.push_to_hub("distilbert-base-multilingual-cased-sentiments-student")
   
 ```