code fixed

README.md

@@ -24,7 +24,7 @@ More information about the original pre-trained model can be found [here](https:
 * Classification examples:
 |Prediction | Input |
 |---------|------------|
-|0 | "selective kindness : in europe , some refugees are more equal than others" |
+|0 | selective kindness : in europe , some refugees are more equal than others |
 |1 | he said their efforts should not stop only at creating many graduates but also extended to students from poor families so that they could break away from the cycle of poverty |
 
 ### How to use
@@ -32,8 +32,8 @@ More information about the original pre-trained model can be found [here](https:
 ```python
 from transformers import T5ForConditionalGeneration, T5Tokenizer
 import torch
-tokenizer = T5Tokenizer.from_pretrained("tosin/pcl_22")
 model = T5ForConditionalGeneration.from_pretrained("tosin/pcl_22")
+tokenizer = T5Tokenizer.from_pretrained("t5-base") # use the source tokenizer because T5 finetuned tokenizer breaks
 tokenizer.pad_token = tokenizer.eos_token
 input_ids = tokenizer("he said their efforts should not stop only at creating many graduates but also extended to students from poor families so that they could break away from the cycle of poverty", padding=True, truncation=True, return_tensors='pt').input_ids
 outputs = model.generate(input_ids)