pierreguillou commited on
Commit
ee3c0fb
1 Parent(s): e5bd1cd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -51,6 +51,8 @@ Due to the small size of the finetuning dataset, the model overfitted before to
51
  - **recall**: 0.9191397849462366
52
  - **accuracy**: 0.9808310603867311
53
  - **loss**: 0.1228889599442482
 
 
54
 
55
  **Note**: the model [pierreguillou/bert-large-cased-pt-lenerbr](https://huggingface.co/pierreguillou/bert-large-cased-pt-lenerbr) is a language model that was created through the finetuning of the model [BERTimbau large](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the dataset [LeNER-Br language modeling](https://huggingface.co/datasets/pierreguillou/lener_br_finetuning_language_model) by using a MASK objective. This first specialization of the language model before finetuning on the NER task allows to get a better NER model.
56
 
@@ -58,6 +60,8 @@ Due to the small size of the finetuning dataset, the model overfitted before to
58
 
59
  You can test this model into the widget of this page.
60
 
 
 
61
  ## Using the model for inference in production
62
  ````
63
  # install pytorch: check https://pytorch.org/
 
51
  - **recall**: 0.9191397849462366
52
  - **accuracy**: 0.9808310603867311
53
  - **loss**: 0.1228889599442482
54
+
55
+ Check as well the [base version of this model](https://huggingface.co/pierreguillou/ner-bert-base-cased-pt-lenerbr) with a f1 of 0.873.
56
 
57
  **Note**: the model [pierreguillou/bert-large-cased-pt-lenerbr](https://huggingface.co/pierreguillou/bert-large-cased-pt-lenerbr) is a language model that was created through the finetuning of the model [BERTimbau large](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the dataset [LeNER-Br language modeling](https://huggingface.co/datasets/pierreguillou/lener_br_finetuning_language_model) by using a MASK objective. This first specialization of the language model before finetuning on the NER task allows to get a better NER model.
58
 
 
60
 
61
  You can test this model into the widget of this page.
62
 
63
+ Use as well the [NER App](https://huggingface.co/spaces/pierreguillou/ner-bert-pt-lenerbr) that allows comparing the 2 BERT models (base and large) fitted in the NER task with the legal LeNER-Br dataset.
64
+
65
  ## Using the model for inference in production
66
  ````
67
  # install pytorch: check https://pytorch.org/