Upload tokenizer

README.md

@@ -3,12 +3,20 @@ library_name: transformers
 license: mit
 tags: []
 widget:
-- text: "Na et al., 'Monitoring of peptide acylation inside degrading PLGA microspheres by capillary electrophoresis and MALDI-T of mass spectrometry', Journal of Controlled Release, 2003, 291-299, 92, Elsevier B.V."
-  example_title: "Example 1"
-- text: "Ryuichiro Higashinaka et al.: “Automatically Acquiring Causal Expression Patterns from Relation-annotated Corpora to Improve Question Answering for why-Questions”, ACM Transactions on Asian Language Information Processing, Association for Computing Machinery, New York, NY, US, vol. 7, No. 2, Apr. 1, 2008, pp. 1-29, XP058 I 46396, ISSN: 1530-0226. DOI: 10.1145/1362782.1362785."
-  example_title: "Example 2"
-- text: "James W. Stave and Klaus Lindpaintner, Antibody and Antigen Contact Residues Define Epitope and Paratope Size and Structure, The Journal of Immunlogy, Published Jun. 24, 2013, doi:10.4049/jimmunol.1203198."
-  example_title: "Example 3"
+- text: Na et al., 'Monitoring of peptide acylation inside degrading PLGA microspheres
+    by capillary electrophoresis and MALDI-T of mass spectrometry', Journal of Controlled
+    Release, 2003, 291-299, 92, Elsevier B.V.
+  example_title: Example 1
+- text: 'Ryuichiro Higashinaka et al.: “Automatically Acquiring Causal Expression
+    Patterns from Relation-annotated Corpora to Improve Question Answering for why-Questions”,
+    ACM Transactions on Asian Language Information Processing, Association for Computing
+    Machinery, New York, NY, US, vol. 7, No. 2, Apr. 1, 2008, pp. 1-29, XP058 I 46396,
+    ISSN: 1530-0226. DOI: 10.1145/1362782.1362785.'
+  example_title: Example 2
+- text: James W. Stave and Klaus Lindpaintner, Antibody and Antigen Contact Residues
+    Define Epitope and Paratope Size and Structure, The Journal of Immunlogy, Published
+    Jun. 24, 2013, doi:10.4049/jimmunol.1203198.
+  example_title: Example 3
 ---
 
 # Model Card for Model ID

tokenizer_config.json

@@ -41,7 +41,7 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",