JohnSnowLabs
diff --git a/‎docs/_posts/ahmedlone127/2024-12-14-1a5e2b8e_en.md‎
Lines changed: 94 additions & 0 deletions b/‎docs/_posts/ahmedlone127/2024-12-14-1a5e2b8e_en.md‎
Lines changed: 94 additions & 0 deletions
diff --git a/‎docs/_posts/ahmedlone127/2024-12-14-1a5e2b8e_pipeline_en.md‎
Lines changed: 70 additions & 0 deletions b/‎docs/_posts/ahmedlone127/2024-12-14-1a5e2b8e_pipeline_en.md‎
Lines changed: 70 additions & 0 deletions
diff --git a/‎docs/_posts/ahmedlone127/2024-12-14-affilgood_ner_multilingual_pipeline_xx.md‎
Lines changed: 70 additions & 0 deletions b/‎docs/_posts/ahmedlone127/2024-12-14-affilgood_ner_multilingual_pipeline_xx.md‎
Lines changed: 70 additions & 0 deletions
diff --git a/‎docs/_posts/ahmedlone127/2024-12-14-affilgood_ner_multilingual_xx.md‎
Lines changed: 94 additions & 0 deletions b/‎docs/_posts/ahmedlone127/2024-12-14-affilgood_ner_multilingual_xx.md‎
Lines changed: 94 additions & 0 deletions
@@ -0,0 +1,94 @@
+---
+layout: model
+title: English 1a5e2b8e XlmRoBertaForTokenClassification from Osquery
+author: John Snow Labs
+name: 1a5e2b8e
+date: 2024-12-14
+tags: [en, open_source, onnx, token_classification, xlm_roberta, ner]
+task: Named Entity Recognition
+language: en
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: XlmRoBertaForTokenClassification
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained XlmRoBertaForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`1a5e2b8e` is a English model originally trained by Osquery.
+
+{:.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/1a5e2b8e_en_5.5.1_3.0_1734214604186.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/1a5e2b8e_en_5.5.1_3.0_1734214604186.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')
+
+tokenClassifier  = XlmRoBertaForTokenClassification.pretrained("1a5e2b8e","en") \
+     .setInputCols(["documents","token"]) \
+     .setOutputCol("ner")
+
+pipeline = Pipeline().setStages([documentAssembler, tokenizer, tokenClassifier])
+data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new DocumentAssembler()
+    .setInputCols("text")
+    .setOutputCols("document")
+    
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+
+val tokenClassifier = XlmRoBertaForTokenClassification.pretrained("1a5e2b8e", "en")
+    .setInputCols(Array("documents","token")) 
+    .setOutputCol("ner") 
+    
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, tokenClassifier))
+val data = Seq("I love spark-nlp").toDS.toDF("text")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|1a5e2b8e|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document, token]|
+|Output Labels:|[ner]|
+|Language:|en|
+|Size:|769.7 MB|
+
+## References
+
+https://huggingface.co/Osquery/1a5e2b8e
@@ -0,0 +1,70 @@
+---
+layout: model
+title: English 1a5e2b8e_pipeline pipeline XlmRoBertaForTokenClassification from Osquery
+author: John Snow Labs
+name: 1a5e2b8e_pipeline
+date: 2024-12-14
+tags: [en, open_source, pipeline, onnx]
+task: Named Entity Recognition
+language: en
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+annotator: PipelineModel
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained XlmRoBertaForTokenClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`1a5e2b8e_pipeline` is a English model originally trained by Osquery.
+
+{:.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/1a5e2b8e_pipeline_en_5.5.1_3.0_1734214743900.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/1a5e2b8e_pipeline_en_5.5.1_3.0_1734214743900.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
+
+pipeline = PretrainedPipeline("1a5e2b8e_pipeline", lang = "en")
+annotations =  pipeline.transform(df)   
+
+```
+```scala
+
+val pipeline = new PretrainedPipeline("1a5e2b8e_pipeline", lang = "en")
+val annotations = pipeline.transform(df)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|1a5e2b8e_pipeline|
+|Type:|pipeline|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Language:|en|
+|Size:|769.7 MB|
+
+## References
+
+https://huggingface.co/Osquery/1a5e2b8e
+
+## Included Models
+
+- DocumentAssembler
+- TokenizerModel
+- XlmRoBertaForTokenClassification
@@ -0,0 +1,70 @@
+---
+layout: model
+title: Multilingual affilgood_ner_multilingual_pipeline pipeline XlmRoBertaForTokenClassification from SIRIS-Lab
+author: John Snow Labs
+name: affilgood_ner_multilingual_pipeline
+date: 2024-12-14
+tags: [xx, open_source, pipeline, onnx]
+task: Named Entity Recognition
+language: xx
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+annotator: PipelineModel
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained XlmRoBertaForTokenClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`affilgood_ner_multilingual_pipeline` is a Multilingual model originally trained by SIRIS-Lab.
+
+{:.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/affilgood_ner_multilingual_pipeline_xx_5.5.1_3.0_1734213424755.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/affilgood_ner_multilingual_pipeline_xx_5.5.1_3.0_1734213424755.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
+
+pipeline = PretrainedPipeline("affilgood_ner_multilingual_pipeline", lang = "xx")
+annotations =  pipeline.transform(df)   
+
+```
+```scala
+
+val pipeline = new PretrainedPipeline("affilgood_ner_multilingual_pipeline", lang = "xx")
+val annotations = pipeline.transform(df)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|affilgood_ner_multilingual_pipeline|
+|Type:|pipeline|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Language:|xx|
+|Size:|1.0 GB|
+
+## References
+
+https://huggingface.co/SIRIS-Lab/affilgood-NER-multilingual
+
+## Included Models
+
+- DocumentAssembler
+- TokenizerModel
+- XlmRoBertaForTokenClassification
@@ -0,0 +1,94 @@
+---
+layout: model
+title: Multilingual affilgood_ner_multilingual XlmRoBertaForTokenClassification from SIRIS-Lab
+author: John Snow Labs
+name: affilgood_ner_multilingual
+date: 2024-12-14
+tags: [xx, open_source, onnx, token_classification, xlm_roberta, ner]
+task: Named Entity Recognition
+language: xx
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: XlmRoBertaForTokenClassification
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained XlmRoBertaForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`affilgood_ner_multilingual` is a Multilingual model originally trained by SIRIS-Lab.
+
+{:.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/affilgood_ner_multilingual_xx_5.5.1_3.0_1734213370612.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/affilgood_ner_multilingual_xx_5.5.1_3.0_1734213370612.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')
+
+tokenClassifier  = XlmRoBertaForTokenClassification.pretrained("affilgood_ner_multilingual","xx") \
+     .setInputCols(["documents","token"]) \
+     .setOutputCol("ner")
+
+pipeline = Pipeline().setStages([documentAssembler, tokenizer, tokenClassifier])
+data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new DocumentAssembler()
+    .setInputCols("text")
+    .setOutputCols("document")
+    
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+
+val tokenClassifier = XlmRoBertaForTokenClassification.pretrained("affilgood_ner_multilingual", "xx")
+    .setInputCols(Array("documents","token")) 
+    .setOutputCol("ner") 
+    
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, tokenClassifier))
+val data = Seq("I love spark-nlp").toDS.toDF("text")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|affilgood_ner_multilingual|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document, token]|
+|Output Labels:|[ner]|
+|Language:|xx|
+|Size:|1.0 GB|
+
+## References
+
+https://huggingface.co/SIRIS-Lab/affilgood-NER-multilingual