Spaces:
Running
Running
updated help string
Browse filesupdated help string to show default values explicitly
- harim_plus.py +4 -4
harim_plus.py
CHANGED
@@ -66,10 +66,10 @@ Args:
|
|
66 |
For scorer.compute():
|
67 |
`predictions` (list of str): generated summaries
|
68 |
`references` (list of str): source articles to be summarized
|
69 |
-
`use_aggregator` (bool): if True, average of the scores are returned
|
70 |
-
`bsz` (int): batch size for harim to iterate through the given pairs
|
71 |
-
`return_details` (bool): whether to show more than harim+ score (returns logppl, harim term. refer to the paper for detail)
|
72 |
-
`tokenwise_score` (bool): whether to show tokenwise scores for input pairs (if return_details=False, this is ignored)
|
73 |
|
74 |
Returns:
|
75 |
'results' (list of float): harim+ score for each summary-article pair
|
|
|
66 |
For scorer.compute():
|
67 |
`predictions` (list of str): generated summaries
|
68 |
`references` (list of str): source articles to be summarized
|
69 |
+
`use_aggregator` (bool=False): if True, average of the scores are returned
|
70 |
+
`bsz` (int=32): batch size for harim to iterate through the given pairs
|
71 |
+
`return_details` (bool=False): whether to show more than harim+ score (returns logppl, harim term. refer to the paper for detail)
|
72 |
+
`tokenwise_score` (bool=False): whether to show tokenwise scores for input pairs (if return_details=False, this is ignored)
|
73 |
|
74 |
Returns:
|
75 |
'results' (list of float): harim+ score for each summary-article pair
|