JohnSnowLabs
diff --git a/‎docs/_posts/ahmedlone127/2023-06-21-bert_base_uncased_contracts_en.md‎
Lines changed: 149 additions & 0 deletions b/‎docs/_posts/ahmedlone127/2023-06-21-bert_base_uncased_contracts_en.md‎
Lines changed: 149 additions & 0 deletions
diff --git a/‎docs/_posts/ahmedlone127/2023-06-21-bert_embeddings_ARBERT_ar.md‎
Lines changed: 149 additions & 0 deletions b/‎docs/_posts/ahmedlone127/2023-06-21-bert_embeddings_ARBERT_ar.md‎
Lines changed: 149 additions & 0 deletions
@@ -0,0 +1,149 @@
+---
+layout: model
+title: English Legal Contracts BertEmbeddings model (Base, Uncased)
+author: John Snow Labs
+name: bert_base_uncased_contracts
+date: 2023-06-21
+tags: [open_source, bert, embeddings, finance, contracts, en, onnx]
+task: Embeddings
+language: en
+edition: Spark NLP 5.0.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BertEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained Word Embeddings model, trained on legal contracts, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-uncased-contracts` is a English model originally trained by `nlpaueb`.
+
+## Predicted Entities
+
+
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_contracts_en_5.0.0_3.0_1687337099443.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_contracts_en_5.0.0_3.0_1687337099443.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+documentAssembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+  
+embeddings = BertEmbeddings.pretrained("bert_base_uncased_contracts","en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings")
+    
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
+
+data = spark.createDataFrame([["I love Spark NLP."]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+      .setInputCol("text") 
+      .setOutputCol("document")
+ 
+val tokenizer = new Tokenizer() 
+    .setInputCols(Array("document"))
+    .setOutputCol("token")
+
+val embeddings = BertEmbeddings.pretrained("bert_base_uncased_contracts","en") 
+    .setInputCols(Array("document", "token")) 
+    .setOutputCol("embeddings")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP.").toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+
+
+{:.nlu-block}
+```python
+import nlu
+nlu.load("en.embed.bert.contracts.uncased_base").predict("""I love Spark NLP.""")
+```
+
+</div>
+
+{:.model-param}
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+documentAssembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+  
+embeddings = BertEmbeddings.pretrained("bert_base_uncased_contracts","en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings")
+    
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
+
+data = spark.createDataFrame([["I love Spark NLP."]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+      .setInputCol("text") 
+      .setOutputCol("document")
+ 
+val tokenizer = new Tokenizer() 
+    .setInputCols(Array("document"))
+    .setOutputCol("token")
+
+val embeddings = BertEmbeddings.pretrained("bert_base_uncased_contracts","en") 
+    .setInputCols(Array("document", "token")) 
+    .setOutputCol("embeddings")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP.").toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+
+{:.nlu-block}
+```python
+import nlu
+nlu.load("en.embed.bert.contracts.uncased_base").predict("""I love Spark NLP.""")
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_base_uncased_contracts|
+|Compatibility:|Spark NLP 5.0.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[bert]|
+|Language:|en|
+|Size:|407.1 MB|
+|Case sensitive:|true|
@@ -0,0 +1,149 @@
+---
+layout: model
+title: Arabic Bert Embeddings (ARBERT model)
+author: John Snow Labs
+name: bert_embeddings_ARBERT
+date: 2023-06-21
+tags: [bert, embeddings, ar, open_source, onnx]
+task: Embeddings
+language: ar
+edition: Spark NLP 5.0.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BertEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained Bert Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. `ARBERT` is a Arabic model orginally trained by `UBC-NLP`.
+
+## Predicted Entities
+
+
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_embeddings_ARBERT_ar_5.0.0_3.0_1687368387135.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_embeddings_ARBERT_ar_5.0.0_3.0_1687368387135.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+documentAssembler = DocumentAssembler() \
+.setInputCol("text") \
+.setOutputCol("document")
+
+tokenizer = Tokenizer() \
+.setInputCols("document") \
+.setOutputCol("token")
+
+embeddings = BertEmbeddings.pretrained("bert_embeddings_ARBERT","ar") \
+.setInputCols(["document", "token"]) \
+.setOutputCol("embeddings")
+
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
+
+data = spark.createDataFrame([["أنا أحب شرارة NLP"]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+.setInputCol("text") 
+.setOutputCol("document")
+
+val tokenizer = new Tokenizer() 
+.setInputCols(Array("document"))
+.setOutputCol("token")
+
+val embeddings = BertEmbeddings.pretrained("bert_embeddings_ARBERT","ar") 
+.setInputCols(Array("document", "token")) 
+.setOutputCol("embeddings")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("أنا أحب شرارة NLP").toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+
+
+{:.nlu-block}
+```python
+import nlu
+nlu.load("ar.embed.arbert").predict("""أنا أحب شرارة NLP""")
+```
+
+</div>
+
+{:.model-param}
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+documentAssembler = DocumentAssembler() \
+.setInputCol("text") \
+.setOutputCol("document")
+
+tokenizer = Tokenizer() \
+.setInputCols("document") \
+.setOutputCol("token")
+
+embeddings = BertEmbeddings.pretrained("bert_embeddings_ARBERT","ar") \
+.setInputCols(["document", "token"]) \
+.setOutputCol("embeddings")
+
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
+
+data = spark.createDataFrame([["أنا أحب شرارة NLP"]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+.setInputCol("text") 
+.setOutputCol("document")
+
+val tokenizer = new Tokenizer() 
+.setInputCols(Array("document"))
+.setOutputCol("token")
+
+val embeddings = BertEmbeddings.pretrained("bert_embeddings_ARBERT","ar") 
+.setInputCols(Array("document", "token")) 
+.setOutputCol("embeddings")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("أنا أحب شرارة NLP").toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+
+{:.nlu-block}
+```python
+import nlu
+nlu.load("ar.embed.arbert").predict("""أنا أحب شرارة NLP""")
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_embeddings_ARBERT|
+|Compatibility:|Spark NLP 5.0.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[bert]|
+|Language:|ar|
+|Size:|605.3 MB|
+|Case sensitive:|true|