chore: Update models with paper and code sources

app.py

@@ -14,7 +14,6 @@ iface = gr.Interface(
                           placeholder="US9820315B2 or https://patents.google.com/patent/US9820315B2 ...", 
                           lines=1,
                           default="US9820315B2"),
-        # gr.inputs.Radio(["Link", "Patent Code"]), # Can be figured out automatically via parsing
         gr.inputs.CheckboxGroup(summarizer.summary_options, 
                                 default=summarizer.summary_options,
                                 label="Summaries to Generate"),
@@ -32,7 +31,7 @@ iface = gr.Interface(
                            optional=False),
         gr.inputs.Slider(minimum=250,
                          maximum=1000,
-                         step=5,
+                         step=10,
                          default=250,
                          label="Input Document Word Limit"),
     ],
@@ -59,10 +58,18 @@ iface = gr.Interface(
     📑 Returns summaries for the abstract, background, and/or claims.
     
     Models explored:
-    - https://huggingface.co/google/bigbird-pegasus-large-bigpatent
-    - https://huggingface.co/cnicu/t5-small-booksum
-    - https://huggingface.co/sshleifer/distilbart-cnn-6-6
-    - https://huggingface.co/google/pegasus-xsum
+    - Big Bird: Transformers for Longer Sequences
+    https://arxiv.org/abs/2007.14062
+    https://huggingface.co/google/bigbird-pegasus-large-bigpatent
+    - T5
+    https://arxiv.org/pdf/1910.10683.pdf
+    https://huggingface.co/cnicu/t5-small-booksum
+    - BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension 
+    https://arxiv.org/abs/1910.13461
+    https://huggingface.co/sshleifer/distilbart-cnn-6-6
+    - PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
+    https://arxiv.org/abs/1912.08777
+    https://huggingface.co/google/pegasus-xsum
     """
 )