update demo link

README.md

@@ -280,15 +280,14 @@ model-index:
 
 # Longformer Encoder-Decoder (LED) fine-tuned on Booksum
 
-demo:
 
- [![colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/pszemraj/d9a0495861776168fd5cdcd7731bc4ee/example-long-t5-tglobal-base-16384-book-summary.ipynb)
+ [![colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/pszemraj/3eba944ddc9fc9a4a1bfb21e83b57620/summarization-token-batching.ipynb)
 
 - A fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the BookSum dataset.
-- Goal: a model that can generalize well and is useful in summarizing long text in academic and daily usage.
+- Goal: a model that can generalize well and is useful in summarizing long text in academic and daily usage. See the demo linked above!
 - works well on lots of text and can handle 16384 tokens/batch (_if you have the GPU memory to handle that_)
 
-> Note: the API is set to generate a max of 64 tokens for runtime reasons, so the summaries may be truncated (depending on length of input text). For best results use python as below.
+> Note: the API is set to generate a max of 64 tokens for runtime reasons, so the summaries may be truncated (depending on the length of input text). For best results use python as below.
 
 ---
 
@@ -366,7 +365,7 @@ The following hyperparameters were used during training:
 
 #### In-between Epochs
 
-Unfortunately, don't have all records on-hand for middle epochs, the following should be representative:
+Unfortunately, don't have all records on-hand for middle epochs; the following should be representative:
 
 - learning_rate: 4e-05
 - train_batch_size: 2