pszemraj commited on
Commit
fb142a6
1 Parent(s): 94ac8b3
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -257,11 +257,12 @@ model-index:
257
 
258
  ---
259
 
260
- # Usage - Basics
261
 
262
- - it is recommended to use `encoder_no_repeat_ngram_size=3` when calling the pipeline object to improve summary quality.
263
- - this param forces the model to use new vocabulary and create an abstractive summary, otherwise it may compile the best _extractive_ summary from the input provided.
264
- - create the pipeline object:
 
265
 
266
  ```python
267
  import torch
257
 
258
  ---
259
 
260
+ # Usage - Basic
261
 
262
+ - use `encoder_no_repeat_ngram_size=3` when calling the pipeline object to improve summary quality.
263
+ - this forces the model to use new vocabulary and create an abstractive summary, otherwise it may compile the best _extractive_ summary from the input provided.
264
+
265
+ Load the model into a pipeline object:
266
 
267
  ```python
268
  import torch