Merge branch 'develop'

CHANGELOG.md

@@ -6,6 +6,18 @@ Most recent releases are shown at the top. Each release shows:
 - **Changed**: Additional parameters, changes to inputs or outputs, etc
 - **Fixed**: Bug fixes that don't change documented behaviour
 
+## 0.29.2 (2022-02-09)
+
+### new:
+- N/A
+
+### changed
+- N/A
+
+### fixed:
+- added `get_tokenizer` call to `TransformersPreprocessor._load_pretrained` to address issue #416
+
+
 ## 0.29.1 (2022-02-08)
 
 ### new:

ktrain/text/preprocessor.py

@@ -1076,6 +1076,8 @@ def _load_pretrained(self, mname, num_labels):
                     #raise ValueError('could not load pretrained model %s using both from_pt=False and from_pt=True' % (mname))
         else:
             model = self.model_type.from_pretrained(mname, num_labels=num_labels)
+        # ISSUE 416: mname is either model name (e.g., bert-base-uncased) or path to folder with tokenizer files
+        self.get_tokenizer(mname)
         return model
 
 

ktrain/version.py

@@ -1,2 +1,2 @@
 __all__ = ['__version__']
-__version__ = '0.29.1'
+__version__ = '0.29.2'