Update README.md

README.md

@@ -23,7 +23,7 @@ Legal_BERTimbau Large is a fine-tuned BERT model based on [BERTimbau](https://hu
 
 For further information or requests, please go to [BERTimbau repository](https://github.com/neuralmind-ai/portuguese-bert/)."
 
-The performance of Language Models can change drastically when there is a domain shift between training and test data. In order create a Portuguese Language Model adapted to a Legal domain, the original BERTimbau model was submitted to a fine-tuning stage where it was performed 1 "PreTraining" epoch over 200000 cleaned documents (lr: 2e-5, using TSDAE technique)
+The performance of Language Models can change drastically when there is a domain shift between training and test data. In order create a Portuguese Language Model adapted to a Legal domain, the original BERTimbau model was submitted to a fine-tuning stage where it was performed 1 "PreTraining" epoch over 200000 cleaned documents (lr: 1e-5, using TSDAE technique)
 
 
 ## Available models
@@ -38,7 +38,7 @@ The performance of Language Models can change drastically when there is a domain
 ```python
 from transformers import AutoTokenizer, AutoModelForMaskedLM
 
-tokenizer = AutoTokenizer.from_pretrained("rufimelo/Legal-BERTimbau-large-TSDAE")
+tokenizer = AutoTokenizer.from_pretrained("rufimelo/Legal-BERTimbau-large-TSDAE-v3")
 
 model = AutoModelForMaskedLM.from_pretrained("rufimelo/Legal-BERTimbau-large-TSDAE")
 ```
@@ -49,8 +49,8 @@ model = AutoModelForMaskedLM.from_pretrained("rufimelo/Legal-BERTimbau-large-TSD
 from  transformers  import  pipeline
 from  transformers  import  AutoTokenizer, AutoModelForMaskedLM
 
-tokenizer = AutoTokenizer.from_pretrained("rufimelo/Legal-BERTimbau-large-TSDAE")
-model = AutoModelForMaskedLM.from_pretrained("rufimelo/Legal-BERTimbau-large-TSDAE")
+tokenizer = AutoTokenizer.from_pretrained("rufimelo/Legal-BERTimbau-large-TSDAE-v3")
+model = AutoModelForMaskedLM.from_pretrained("rufimelo/Legal-BERTimbau-large-TSDAE-v3")
 
 pipe = pipeline('fill-mask', model=model, tokenizer=tokenizer)
 pipe('O advogado apresentou [MASK] para o juíz')