2025-06-23-minilm_l6_v2_en

docs/_posts/prabod/2025-06-23-minilm_l6_v2_en.md

@@ -0,0 +1,120 @@
+---
+layout: model
+title: MiniLM L6 V2
+author: John Snow Labs
+name: minilm_l6_v2
+date: 2025-06-23
+tags: [en, open_source, openvino]
+task: Embeddings
+language: en
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+engine: openvino
+annotator: MiniLMEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Sentence embeddings using MiniLM.
+
+MiniLM, a lightweight and efficient sentence embedding model that can generate text embeddings
+for various NLP tasks (e.g., classification, retrieval, clustering, text evaluation, etc.)
+
+## 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/minilm_l6_v2_en_5.5.1_3.0_1750674121132.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/minilm_l6_v2_en_5.5.1_3.0_1750674121132.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
+import sparknlp
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+documentAssembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("document")
+embeddings = MiniLMEmbeddings.pretrained() \
+    .setInputCols(["document"]) \
+    .setOutputCol("minilm_embeddings")
+embeddingsFinisher = EmbeddingsFinisher() \
+    .setInputCols(["minilm_embeddings"]) \
+    .setOutputCols("finished_embeddings") \
+    .setOutputAsVector(True)
+pipeline = Pipeline().setStages([
+    documentAssembler,
+    embeddings,
+    embeddingsFinisher
+])
+
+data = spark.createDataFrame([["This is a sample sentence for embedding generation.",
+    "Another example sentence to demonstrate MiniLM embeddings.",
+]]).toDF("text")
+result = pipeline.fit(data).transform(data)
+result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+```
+```scala
+import spark.implicits._
+import com.johnsnowlabs.nlp.base.DocumentAssembler
+import com.johnsnowlabs.nlp.annotators.Tokenizer
+import com.johnsnowlabs.nlp.embeddings.MiniLMEmbeddings
+import com.johnsnowlabs.nlp.EmbeddingsFinisher
+import org.apache.spark.ml.Pipeline
+
+val documentAssembler = new DocumentAssembler()
+  .setInputCol("text")
+  .setOutputCol("document")
+
+val embeddings = MiniLMEmbeddings.pretrained("minilm_l6_v2", "en")
+  .setInputCols("document")
+  .setOutputCol("minilm_embeddings")
+
+val embeddingsFinisher = new EmbeddingsFinisher()
+  .setInputCols("minilm_embeddings")
+  .setOutputCols("finished_embeddings")
+  .setOutputAsVector(true)
+
+val pipeline = new Pipeline().setStages(Array(
+  documentAssembler,
+  embeddings,
+  embeddingsFinisher
+))
+
+val data = Seq("This is a sample sentence for embedding generation.",
+"Another example sentence to demonstrate MiniLM embeddings."
+
+).toDF("text")
+val result = pipeline.fit(data).transform(data)
+
+result.selectExpr("explode(finished_embeddings) as result").show(1, 80)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|minilm_l6_v2|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[minilm]|
+|Language:|en|
+|Size:|17.2 MB|