2023-08-25-e5_small_en (#13939)

* Add model 2023-08-25-e5_small_en * Add model 2023-08-25-e5_small_opt_en * Add model 2023-08-25-e5_small_quantized_en * Add model 2023-08-25-e5_base_en * Add model 2023-08-25-e5_small_v2_opt_en * Add model 2023-08-25-e5_base_opt_en * Add model 2023-08-25-e5_base_quantized_en * Add model 2023-08-25-e5_small_v2_en * Add model 2023-08-25-e5_small_v2_quantized_en * Add model 2023-08-25-e5_base_v2_en * Add model 2023-08-25-e5_base_v2_opt_en * Add model 2023-08-25-e5_base_v2_quantized_en * Add model 2023-08-25-e5_large_v2_en --------- Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>
JohnSnowLabs · Aug 25, 2023 · b1b99f5 · b1b99f5
1 parent 06f07da
commit b1b99f5
Show file tree

Hide file tree

Showing 13 changed files with 874 additions and 0 deletions.
diff --git a/docs/_posts/ahmedlone127/2023-08-25-e5_base_en.md b/docs/_posts/ahmedlone127/2023-08-25-e5_base_en.md
@@ -0,0 +1,67 @@
+---
+layout: model
+title: E5 Base Sentence Embeddings
+author: John Snow Labs
+name: e5_base
+date: 2023-08-25
+tags: [en, open_source, onnx]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: E5Embeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
+
+## 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/e5_base_en_5.1.0_3.0_1692963566674.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/e5_base_en_5.1.0_3.0_1692963566674.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
+embeddings =E5Embeddings.pretrained("e5_base","en") \
+            .setInputCols(["documents"]) \
+            .setOutputCol("instructor")
+
+pipeline = Pipeline().setStages([document_assembler, embeddings])
+```
+```scala
+val embeddings = E5Embeddings.pretrained("e5_base","en")
+      .setInputCols(["document"])
+      .setOutputCol("e5_embeddings")
+val pipeline = new Pipeline().setStages(Array(document, embeddings))
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|e5_base|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[e5]|
+|Language:|en|
+|Size:|258.6 MB|
diff --git a/docs/_posts/ahmedlone127/2023-08-25-e5_base_opt_en.md b/docs/_posts/ahmedlone127/2023-08-25-e5_base_opt_en.md
@@ -0,0 +1,67 @@
+---
+layout: model
+title: E5 Base Sentence Embeddings
+author: John Snow Labs
+name: e5_base_opt
+date: 2023-08-25
+tags: [en, open_source, onnx]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: E5Embeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
+
+## 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/e5_base_opt_en_5.1.0_3.0_1692963694288.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/e5_base_opt_en_5.1.0_3.0_1692963694288.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
+embeddings =E5Embeddings.pretrained("e5_base","en") \
+            .setInputCols(["documents"]) \
+            .setOutputCol("instructor")
+
+pipeline = Pipeline().setStages([document_assembler, embeddings])
+```
+```scala
+val embeddings = E5Embeddings.pretrained("e5_base","en")
+      .setInputCols(["document"])
+      .setOutputCol("e5_embeddings")
+val pipeline = new Pipeline().setStages(Array(document, embeddings))
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|e5_base_opt|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[e5]|
+|Language:|en|
+|Size:|258.7 MB|
diff --git a/docs/_posts/ahmedlone127/2023-08-25-e5_base_quantized_en.md b/docs/_posts/ahmedlone127/2023-08-25-e5_base_quantized_en.md
@@ -0,0 +1,67 @@
+---
+layout: model
+title: E5 Base Sentence Embeddings
+author: John Snow Labs
+name: e5_base_quantized
+date: 2023-08-25
+tags: [en, open_source, onnx]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: E5Embeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
+
+## 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/e5_base_quantized_en_5.1.0_3.0_1692963757236.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/e5_base_quantized_en_5.1.0_3.0_1692963757236.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
+embeddings =E5Embeddings.pretrained("e5_base","en") \
+            .setInputCols(["documents"]) \
+            .setOutputCol("instructor")
+
+pipeline = Pipeline().setStages([document_assembler, embeddings])
+```
+```scala
+val embeddings = E5Embeddings.pretrained("e5_base","en")
+      .setInputCols(["document"])
+      .setOutputCol("e5_embeddings")
+val pipeline = new Pipeline().setStages(Array(document, embeddings))
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|e5_base_quantized|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[e5]|
+|Language:|en|
+|Size:|67.1 MB|
diff --git a/docs/_posts/ahmedlone127/2023-08-25-e5_base_v2_en.md b/docs/_posts/ahmedlone127/2023-08-25-e5_base_v2_en.md
@@ -0,0 +1,68 @@
+---
+layout: model
+title: E5 Base v2 Sentence Embeddings
+author: John Snow Labs
+name: e5_base_v2
+date: 2023-08-25
+tags: [e5, sentence_embeddings, en, open_source, onnx]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: E5Embeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
+
+## 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/e5_base_v2_en_5.1.0_3.0_1692964050132.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/e5_base_v2_en_5.1.0_3.0_1692964050132.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
+embeddings =E5Embeddings.pretrained("e5_base_v2","en") \
+            .setInputCols(["documents"]) \
+            .setOutputCol("instructor")
+
+pipeline = Pipeline().setStages([document_assembler, embeddings])
+```
+```scala
+val embeddings = E5Embeddings.pretrained("e5_base_v2","en")
+      .setInputCols(["document"])
+      .setOutputCol("e5_embeddings")
+
+val pipeline = new Pipeline().setStages(Array(document, embeddings))
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|e5_base_v2|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[e5]|
+|Language:|en|
+|Size:|258.7 MB|
diff --git a/docs/_posts/ahmedlone127/2023-08-25-e5_base_v2_opt_en.md b/docs/_posts/ahmedlone127/2023-08-25-e5_base_v2_opt_en.md
@@ -0,0 +1,68 @@
+---
+layout: model
+title: E5 Base v2 Sentence Embeddings
+author: John Snow Labs
+name: e5_base_v2_opt
+date: 2023-08-25
+tags: [e5, sentence_embeddings, en, open_source, onnx]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: E5Embeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
+
+## 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/e5_base_v2_opt_en_5.1.0_3.0_1692964193495.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/e5_base_v2_opt_en_5.1.0_3.0_1692964193495.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
+embeddings =E5Embeddings.pretrained("e5_base_v2","en") \
+            .setInputCols(["documents"]) \
+            .setOutputCol("instructor")
+
+pipeline = Pipeline().setStages([document_assembler, embeddings])
+```
+```scala
+val embeddings = E5Embeddings.pretrained("e5_base_v2","en")
+      .setInputCols(["document"])
+      .setOutputCol("e5_embeddings")
+
+val pipeline = new Pipeline().setStages(Array(document, embeddings))
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|e5_base_v2_opt|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[e5]|
+|Language:|en|
+|Size:|258.8 MB|