pszemraj
/

led-large-book-summary

Summarization Transformers PyTorch Safetensors

led text2text-generation summary longformer booksum long-document long-form Eval Results Inference Endpoints

Model card Files Files and versions Community

pszemraj commited on Jun 2, 2022

Commit

2e4030b

•

1 Parent(s): b6289aa

update inference params

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -59,12 +59,12 @@ Nearby tokens should be important because, in a sentence (sequence of words), th
 inference:
   parameters:
     max_length: 64
-    min_length: 4
-    no_repeat_ngram_size: 2
     early_stopping: True
-    repetition_penalty: 2.4
-    length_penalty: 0.3
-    encoder_no_repeat_ngram_size : 3
     num_beams : 4

 inference:
   parameters:
     max_length: 64
+    min_length: 8
+    no_repeat_ngram_size: 3
     early_stopping: True
+    repetition_penalty: 3.5
+    length_penalty: 0.1
+    encoder_no_repeat_ngram_size : 4
     num_beams : 4