matejulcar commited on
Commit
a4fe4c3
1 Parent(s): e3529a6

Minor update to readme

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ from transformers import AutoTokenizer, AutoModelForMaskedLM
12
  tokenizer = AutoTokenizer.from_pretrained("EMBEDDIA/sloberta", use_fast=False)
13
  model = AutoModelForMaskedLM.from_pretrained("EMBEDDIA/sloberta")
14
  ```
15
- **NOTE**: it is currently *critically important* to add `use_fast=False` parameter to tokenizer. By default it attempts to load a fast tokenizer, which will work (ie. not result in an error), but it will not correctly map tokens to its IDs and the performance on any task will be extremely bad.
16
 
17
  # SloBERTa
18
  SloBERTa model is a monolingual Slovene BERT-like model. It is closely related to French Camembert model https://camembert-model.fr/. The corpora used for training the model have 3.47 billion tokens in total. The subword vocabulary contains 32,000 tokens. The scripts and programs used for data preparation and training the model are available on https://github.com/clarinsi/Slovene-BERT-Tool
 
12
  tokenizer = AutoTokenizer.from_pretrained("EMBEDDIA/sloberta", use_fast=False)
13
  model = AutoModelForMaskedLM.from_pretrained("EMBEDDIA/sloberta")
14
  ```
15
+ **NOTE**: it is currently *critically important* to add `use_fast=False` parameter to tokenizer if using transformers version 4+ (prior versions have `use_fast=False` as default) By default it attempts to load a fast tokenizer, which will work (ie. not result in an error), but it will not correctly map tokens to its IDs and the performance on any task will be extremely bad.
16
 
17
  # SloBERTa
18
  SloBERTa model is a monolingual Slovene BERT-like model. It is closely related to French Camembert model https://camembert-model.fr/. The corpora used for training the model have 3.47 billion tokens in total. The subword vocabulary contains 32,000 tokens. The scripts and programs used for data preparation and training the model are available on https://github.com/clarinsi/Slovene-BERT-Tool