2023-02-20-bert_embeddings_pretrain_ko (#13548)

* Add model 2023-02-20-bert_embeddings_pretrain_ko * Update 2023-02-20-bert_embeddings_pretrain_ko.md * Update 2023-02-20-bert_embeddings_pretrain_ko.md * Add model 2023-02-20-bert_embeddings_base_uncased_issues_128_en * Update 2023-02-20-bert_embeddings_base_uncased_issues_128_en.md * Add model 2023-02-21-chemical_uncased_finetuned_cust_c2_en * Update 2023-02-21-chemical_uncased_finetuned_cust_c2_en.md * Delete 2023-02-21-chemical_uncased_finetuned_cust_c2_en.md * Add model 2023-02-21-bert_embeddings_chemical_uncased_finetuned_cust_c2_en * Update 2023-02-21-bert_embeddings_chemical_uncased_finetuned_cust_c2_en.md * Add model 2023-02-21-bert_embeddings_olm_base_uncased_oct_2022_en * Update 2023-02-21-bert_embeddings_olm_base_uncased_oct_2022_en.md * Add model 2023-02-21-bert_embeddings_chemical_uncased_finetuned_cust_c1_cust_en * Update 2023-02-21-bert_embeddings_chemical_uncased_finetuned_cust_c1_cust_en.md * Add model 2023-02-22-bert_embeddings_carlbert_webex_mlm_spatial_en * Update 2023-02-22-bert_embeddings_carlbert_webex_mlm_spatial_en.md * Add model 2023-02-22-bert_embeddings_distil_clinical_en * Update 2023-02-22-bert_embeddings_distil_clinical_en.md * Add model 2023-02-23-distilbert_embeddings_base_multilingual_cased_xx * Update 2023-02-23-distilbert_embeddings_base_multilingual_cased_xx.md * Add model 2023-02-23-deberta_embeddings_erlangshen_v2_chinese_sentencepiece_zh * Update 2023-02-23-deberta_embeddings_erlangshen_v2_chinese_sentencepiece_zh.md --------- Co-authored-by: Mary-Sci <meryemyildiz366@gmail.com> Co-authored-by: Merve Ertas Uslu <67653613+Mary-Sci@users.noreply.github.com>
JohnSnowLabs · Feb 24, 2023 · 0c314ef · 0c314ef
1 parent 0347607
commit 0c314ef
Show file tree

Hide file tree

Showing 9 changed files with 865 additions and 0 deletions.
diff --git a/docs/_posts/Mary-Sci/2023-02-20-bert_embeddings_base_uncased_issues_128_en.md b/docs/_posts/Mary-Sci/2023-02-20-bert_embeddings_base_uncased_issues_128_en.md
@@ -0,0 +1,97 @@
+---
+layout: model
+title: English Bert Embeddings Cased model (from antoinev17)
+author: John Snow Labs
+name: bert_embeddings_base_uncased_issues_128
+date: 2023-02-20
+tags: [open_source, bert, bert_embeddings, bertformaskedlm, en, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 4.3.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: BertEmbeddings
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-uncased-issues-128` is a English model originally trained by `antoinev17
+`.
+
+{:.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_base_uncased_issues_128_en_4.3.0_3.0_1676927301180.zip){:.button.button-orange}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_embeddings_base_uncased_issues_128_en_4.3.0_3.0_1676927301180.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() \
+    .setInputCols(["text"]) \
+    .setOutputCols("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+
+embeddings = BertEmbeddings.pretrained("bert_embeddings_base_uncased_issues_128","ko") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings") \
+    .setCaseSensitive(True)
+
+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() 
+    .setInputCols(Array("text")) 
+    .setOutputCols(Array("document"))
+
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+
+val embeddings = BertEmbeddings.pretrained("bert_embeddings_base_uncased_issues_128","ko") 
+    .setInputCols(Array("document", "token"))
+    .setOutputCol("embeddings")
+    .setCaseSensitive(True)    
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_embeddings_base_uncased_issues_128|
+|Compatibility:|Spark NLP 4.3.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[bert]|
+|Language:|en|
+|Size:|410.1 MB|
+|Case sensitive:|true|
+
+## References
+
+https://huggingface.co/antoinev17/bert-base-uncased-issues-128
diff --git a/docs/_posts/Mary-Sci/2023-02-20-bert_embeddings_pretrain_ko.md b/docs/_posts/Mary-Sci/2023-02-20-bert_embeddings_pretrain_ko.md
@@ -0,0 +1,96 @@
+---
+layout: model
+title: Korean Bert Embeddings Cased model (from onlydj96)
+author: John Snow Labs
+name: bert_embeddings_pretrain
+date: 2023-02-20
+tags: [open_source, bert, bert_embeddings, bertformaskedlm, ko, tensorflow]
+task: Embeddings
+language: ko
+edition: Spark NLP 4.3.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: BertEmbeddings
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert_pretrain` is a Korean model originally trained by `onlydj96`.
+
+{:.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_pretrain_ko_4.3.0_3.0_1676925661631.zip){:.button.button-orange}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_embeddings_pretrain_ko_4.3.0_3.0_1676925661631.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() \
+    .setInputCols(["text"]) \
+    .setOutputCols("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+
+embeddings = BertEmbeddings.pretrained("bert_embeddings_pretrain","ko") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings") \
+    .setCaseSensitive(True)
+
+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() 
+    .setInputCols(Array("text")) 
+    .setOutputCols(Array("document"))
+
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+
+val embeddings = BertEmbeddings.pretrained("bert_embeddings_pretrain","ko") 
+    .setInputCols(Array("document", "token"))
+    .setOutputCol("embeddings")
+    .setCaseSensitive(true)    
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_embeddings_pretrain|
+|Compatibility:|Spark NLP 4.3.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[bert]|
+|Language:|ko|
+|Size:|415.5 MB|
+|Case sensitive:|true|
+
+## References
+
+https://huggingface.co/onlydj96/bert_pretrain
diff --git a/...ry-Sci/2023-02-21-bert_embeddings_chemical_uncased_finetuned_cust_c1_cust_en.md b/...ry-Sci/2023-02-21-bert_embeddings_chemical_uncased_finetuned_cust_c1_cust_en.md
@@ -0,0 +1,96 @@
+---
+layout: model
+title: English Bert Embeddings Cased model (from Shafin)
+author: John Snow Labs
+name: bert_embeddings_chemical_uncased_finetuned_cust_c1_cust
+date: 2023-02-21
+tags: [open_source, bert, bert_embeddings, bertformaskedlm, en, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 4.3.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: BertEmbeddings
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `chemical-bert-uncased-finetuned-cust-c1-cust` is a English model originally trained by `Shafin`.
+
+{:.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_chemical_uncased_finetuned_cust_c1_cust_en_4.3.0_3.0_1677001598364.zip){:.button.button-orange}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_embeddings_chemical_uncased_finetuned_cust_c1_cust_en_4.3.0_3.0_1677001598364.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() \
+    .setInputCols(["text"]) \
+    .setOutputCols("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+
+embeddings = BertEmbeddings.pretrained("bert_embeddings_chemical_uncased_finetuned_cust_c1_cust","en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings") \
+    .setCaseSensitive(True)
+
+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() 
+    .setInputCols(Array("text")) 
+    .setOutputCols(Array("document"))
+
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+
+val embeddings = BertEmbeddings.pretrained("bert_embeddings_chemical_uncased_finetuned_cust_c1_cust","en") 
+    .setInputCols(Array("document", "token"))
+    .setOutputCol("embeddings")
+    .setCaseSensitive(True)    
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_embeddings_chemical_uncased_finetuned_cust_c1_cust|
+|Compatibility:|Spark NLP 4.3.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[bert]|
+|Language:|en|
+|Size:|412.1 MB|
+|Case sensitive:|true|
+
+## References
+
+https://huggingface.co/shafin/chemical-bert-uncased-finetuned-cust-c1-cust
diff --git a/...ts/Mary-Sci/2023-02-21-bert_embeddings_chemical_uncased_finetuned_cust_c2_en.md b/...ts/Mary-Sci/2023-02-21-bert_embeddings_chemical_uncased_finetuned_cust_c2_en.md
@@ -0,0 +1,96 @@
+---
+layout: model
+title: English Bert Embeddings Cased model (from Shafin)
+author: John Snow Labs
+name: bert_embeddings_chemical_uncased_finetuned_cust_c2
+date: 2023-02-21
+tags: [open_source, bert, bert_embeddings, bertformaskedlm, en, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 4.3.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: BertEmbeddings
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `chemical-bert-uncased-finetuned-cust-c2` is a English model originally trained by `shafin`.
+
+{:.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_chemical_uncased_finetuned_cust_c2_en_4.3.0_3.0_1676998811176.zip){:.button.button-orange}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_embeddings_chemical_uncased_finetuned_cust_c2_en_4.3.0_3.0_1676998811176.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() \
+    .setInputCols(["text"]) \
+    .setOutputCols("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+
+embeddings = BertEmbeddings.pretrained("bert_embeddings_chemical_uncased_finetuned_cust_c2","en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings") \
+    .setCaseSensitive(True)
+
+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() 
+    .setInputCols(Array("text")) 
+    .setOutputCols(Array("document"))
+
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+
+val embeddings = BertEmbeddings.pretrained("bert_embeddings_chemical_uncased_finetuned_cust_c2","en") 
+    .setInputCols(Array("document", "token"))
+    .setOutputCol("embeddings")
+    .setCaseSensitive(True)    
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_embeddings_chemical_uncased_finetuned_cust_c2|
+|Compatibility:|Spark NLP 4.3.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[bert]|
+|Language:|en|
+|Size:|412.1 MB|
+|Case sensitive:|true|
+
+## References
+
+https://huggingface.co/shafin/chemical-bert-uncased-finetuned-cust-c2