Update README.md

README.md

@@ -35,7 +35,7 @@ inference:
 
 # bigbird pegasus on the booksum dataset 
 
-_this is the "latest" version of the model that has been trained the longest, currently at 70k steps_
+>_this is the "latest" version of the model that has been trained the longest, currently at 70k steps_
 
 - motivation: typical datasets for summarization models are in the vein of PubMed / arXiv; for my use cases, I have found summaries created by models pretrained on these to be useful.
   - summarizing text via arXiv models will typically make the summary sound so needlessly complicated that you might as well have read the original text in that time.
@@ -44,9 +44,11 @@ _this is the "latest" version of the model that has been trained the longest, cu
     - Will continue to improve  (slowly, now that it has been trained for a long time) based on any result findings/feedback.
 - the starting checkpoint was `google/bigbird-pegasus-large-bigpatent`
 
+---
+
 # example usage
 
-> An extended example, including a demo of batch summarization, is [here](https://colab.research.google.com/gist/pszemraj/2c8c0aecbcd4af6e9cbb51e195be10e2/bigbird-pegasus-large-booksum-20k-example.ipynb).
+>An extended example, including a demo of batch summarization, is [here](https://colab.research.google.com/gist/pszemraj/2c8c0aecbcd4af6e9cbb51e195be10e2/bigbird-pegasus-large-booksum-20k-example.ipynb).
 
 
 - create the summarizer object:
@@ -89,6 +91,11 @@ result = summarizer(
 print(result[0]['summary_text'])
 ```
 
+## Alternate Checkpoint
+
+- if experiencing runtime / memory issues, try [this earlier checkpoint](https://huggingface.co/pszemraj/bigbird-pegasus-large-booksum-40k-K) at 40,000 steps which is almost as good at the explanatory summarization task, but runs faster.
+
+---
 
 # Results