2024-01-01-bge_small_en (#14116)

* Add model 2024-01-01-bge_small_en * Add model 2024-01-01-bge_base_en * Add model 2024-01-01-bge_large_en --------- Co-authored-by: maziyarpanahi <[email protected]>
JohnSnowLabs · Jan 1, 2024 · f38ea17 · f38ea17
1 parent 9fa1404
commit f38ea17
Show file tree

Hide file tree

Showing 3 changed files with 257 additions and 0 deletions.
diff --git a/docs/_posts/maziyarpanahi/2024-01-01-bge_base_en.md b/docs/_posts/maziyarpanahi/2024-01-01-bge_base_en.md
@@ -0,0 +1,85 @@
+---
+layout: model
+title: BAAI general embedding English (bge_base)
+author: John Snow Labs
+name: bge_base
+date: 2024-01-01
+tags: [bert, bge, onnx, en, open_source]
+task: Embeddings
+language: en
+edition: Spark NLP 5.2.1
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BGEEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification,  clustering, or semantic search.
+And it also can be used in vector database for LLMs.
+
+`bge` is short for `BAAI general embedding`.
+
+|              Model              | Language | Description | query instruction for retrieval\* |
+|:-------------------------------|:--------:| :--------:| :--------:|
+|  [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) |   English |  rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) |   English |  rank **2nd** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) |   English | a small-scale model but with competitive performance  | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) |   Chinese | rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章：`  |
+|  [BAAI/bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) |   Chinese | This model is trained without instruction, and rank **2nd** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark |   |
+|  [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) |   Chinese |  a base-scale model but has similar ability with `bge-large-zh` | `为这个句子生成表示以用于检索相关文章：`  |
+|  [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) |   Chinese | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：`  |
+
+## 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/bge_base_en_5.2.1_3.0_1704107443716.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bge_base_en_5.2.1_3.0_1704107443716.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
+document = DocumentAssembler()\ 
+    .setInputCol("text")\ 
+    .setOutputCol("document")
+
+embeddings = BGEEmbeddings.pretrained("bge_base", "en")\ 
+    .setInputCols("document")\ 
+    .setOutputCol("embeddings")
+```
+```scala
+val document = new DocumentAssembler()
+  .setInputCol("text")
+  .setOutputCol("document")
+
+val embeddings = BGEEmbeddings.pretrained("bge_base", "en")
+    .setInputCols("document")
+    .setOutputCol("embeddings")
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bge_base|
+|Compatibility:|Spark NLP 5.2.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document]|
+|Output Labels:|[bge]|
+|Language:|en|
+|Size:|258.7 MB|
diff --git a/docs/_posts/maziyarpanahi/2024-01-01-bge_large_en.md b/docs/_posts/maziyarpanahi/2024-01-01-bge_large_en.md
@@ -0,0 +1,87 @@
+---
+layout: model
+title: BAAI general embedding English (bge_large)
+author: John Snow Labs
+name: bge_large
+date: 2024-01-01
+tags: [en, onnx, bert, bge, open_source]
+task: Embeddings
+language: en
+edition: Spark NLP 5.2.1
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BGEEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification,  clustering, or semantic search.
+And it also can be used in vector database for LLMs.
+
+`bge` is short for `BAAI general embedding`.
+
+|              Model              | Language | Description | query instruction for retrieval\* |
+|:-------------------------------|:--------:| :--------:| :--------:|
+|  [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) |   English |  rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) |   English |  rank **2nd** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) |   English | a small-scale model but with competitive performance  | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) |   Chinese | rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章：`  |
+|  [BAAI/bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) |   Chinese | This model is trained without instruction, and rank **2nd** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark |   |
+|  [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) |   Chinese |  a base-scale model but has similar ability with `bge-large-zh` | `为这个句子生成表示以用于检索相关文章：`  |
+|  [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) |   Chinese | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：`  |
+
+## 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/bge_large_en_5.2.1_3.0_1704108288598.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bge_large_en_5.2.1_3.0_1704108288598.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
+document = DocumentAssembler()\ 
+    .setInputCol("text")\ 
+    .setOutputCol("document")
+
+
+embeddings = BGEEmbeddings.pretrained("bge_large", "en")\ 
+    .setInputCols("document")\ 
+    .setOutputCol("embeddings")
+```
+```scala
+val document = new DocumentAssembler()
+  .setInputCol("text")
+  .setOutputCol("document")
+
+
+val embeddings = BGEEmbeddings.pretrained("bge_large", "en")
+    .setInputCols("document")
+    .setOutputCol("embeddings")
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bge_large|
+|Compatibility:|Spark NLP 5.2.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document]|
+|Output Labels:|[bge]|
+|Language:|en|
+|Size:|794.1 MB|
diff --git a/docs/_posts/maziyarpanahi/2024-01-01-bge_small_en.md b/docs/_posts/maziyarpanahi/2024-01-01-bge_small_en.md
@@ -0,0 +1,85 @@
+---
+layout: model
+title: BAAI general embedding English (bge_small)
+author: John Snow Labs
+name: bge_small
+date: 2024-01-01
+tags: [onnx, bert, bge, en, open_source]
+task: Embeddings
+language: en
+edition: Spark NLP 5.2.1
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BGEEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification,  clustering, or semantic search.
+And it also can be used in vector database for LLMs.
+
+`bge` is short for `BAAI general embedding`.
+
+|              Model              | Language | Description | query instruction for retrieval\* |
+|:-------------------------------|:--------:| :--------:| :--------:|
+|  [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) |   English |  rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) |   English |  rank **2nd** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) |   English | a small-scale model but with competitive performance  | `Represent this sentence for searching relevant passages: `  |
+|  [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) |   Chinese | rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章：`  |
+|  [BAAI/bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) |   Chinese | This model is trained without instruction, and rank **2nd** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark |   |
+|  [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) |   Chinese |  a base-scale model but has similar ability with `bge-large-zh` | `为这个句子生成表示以用于检索相关文章：`  |
+|  [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) |   Chinese | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：`  |
+
+## 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/bge_small_en_5.2.1_3.0_1704105455110.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bge_small_en_5.2.1_3.0_1704105455110.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
+document = DocumentAssembler()\ 
+    .setInputCol("text")\ 
+    .setOutputCol("document")
+
+embeddings = BGEEmbeddings.pretrained("bge_small", "en")\ 
+    .setInputCols("document")\ 
+    .setOutputCol("embeddings")
+```
+```scala
+val document = new DocumentAssembler()
+  .setInputCol("text")
+  .setOutputCol("document")
+
+val embeddings = BGEEmbeddings.pretrained("bge_small", "en")
+    .setInputCols("document")
+    .setOutputCol("embeddings")
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bge_small|
+|Compatibility:|Spark NLP 5.2.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document]|
+|Output Labels:|[bge]|
+|Language:|en|
+|Size:|79.8 MB|