Merge branch 'master' into release/552-release-candidate

JohnSnowLabs · Dec 9, 2024 · 48c61bb · 48c61bb
2 parents 59f91bc + 2482436
commit 48c61bb
Show file tree

Hide file tree

Showing 6 changed files with 535 additions and 0 deletions.
diff --git a/docs/_posts/ahmedlone127/2024-11-26-mini_cpm_2b_8bit_xx.md b/docs/_posts/ahmedlone127/2024-11-26-mini_cpm_2b_8bit_xx.md
@@ -0,0 +1,86 @@
+---
+layout: model
+title: mini_cpm_2b_8bit model from
+author: John Snow Labs
+name: mini_cpm_2b_8bit
+date: 2024-11-26
+tags: [en, open_source, pipeline, openvino, xx]
+task: Text Generation
+language: xx
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+engine: openvino
+annotator: CPMTransformer
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained CPMTransformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mini_cpm_2b_8bit` is a multilingual model originally trained by openbmb.
+
+{:.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/mini_cpm_2b_8bit_xx_5.5.1_3.0_1732658809236.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mini_cpm_2b_8bit_xx_5.5.1_3.0_1732658809236.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")
+
+seq2seq = CPMTransformer.pretrained("mini_cpm_2b_8bit","xx") \
+      .setInputCols(["documents"]) \
+      .setOutputCol("generation")       
+
+pipeline = Pipeline().setStages([documentAssembler, seq2seq])
+data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new DocumentAssembler() 
+    .setInputCol("text") 
+    .setOutputCol("document")
+
+val seq2seq = CPMTransformer.pretrained("mini_cpm_2b_8bit","xx") 
+    .setInputCols(Array("documents")) 
+    .setOutputCol("generation")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, seq2seq))
+val data = Seq("I love spark-nlp").toDF("text")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|mini_cpm_2b_8bit|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[generation]|
+|Language:|xx|
+|Size:|3.0 GB|
+
+## References
+
+https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16
diff --git a/docs/_posts/ahmedlone127/2024-11-27-nllb_distilled_600M_8int_xx.md b/docs/_posts/ahmedlone127/2024-11-27-nllb_distilled_600M_8int_xx.md
@@ -0,0 +1,86 @@
+---
+layout: model
+title: nllb_distilled_600M_8int model from Facebook
+author: John Snow Labs
+name: nllb_distilled_600M_8int
+date: 2024-11-27
+tags: [en, open_source, pipeline, openvino, xx]
+task: Text Generation
+language: xx
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+engine: openvino
+annotator: NLLBTransformer
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained NLLBTransformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`nllb_distilled_600M_8int` is a Multilingual model originally trained by facebook.
+
+{:.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/nllb_distilled_600M_8int_xx_5.5.1_3.0_1732741416718.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/nllb_distilled_600M_8int_xx_5.5.1_3.0_1732741416718.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")
+
+seq2seq = NLLBTransformer.pretrained("mini_cpm_2b_8bit","xx") \
+      .setInputCols(["documents"]) \
+      .setOutputCol("generation")       
+
+pipeline = Pipeline().setStages([documentAssembler, seq2seq])
+data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new DocumentAssembler() 
+    .setInputCol("text") 
+    .setOutputCol("document")
+
+val seq2seq = NLLBTransformer.pretrained("mini_cpm_2b_8bit","xx") 
+    .setInputCols(Array("documents")) 
+    .setOutputCol("generation")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, seq2seq))
+val data = Seq("I love spark-nlp").toDF("text")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|nllb_distilled_600M_8int|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[generation]|
+|Language:|xx|
+|Size:|842.9 MB|
+
+## References
+
+https://huggingface.co/facebook/nllb-200-distilled-600M
diff --git a/docs/_posts/ahmedlone127/2024-11-27-nomic_embed_v1_en.md b/docs/_posts/ahmedlone127/2024-11-27-nomic_embed_v1_en.md
@@ -0,0 +1,86 @@
+---
+layout: model
+title: nomic_embed_v1 model from nomic-ai
+author: John Snow Labs
+name: nomic_embed_v1
+date: 2024-11-27
+tags: [en, open_source, openvino]
+task: Embeddings
+language: en
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+engine: openvino
+annotator: NomicEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained NomicEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mini_cpm_2b_8bit` is a multilingual model originally trained by openbmb.
+
+{:.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/nomic_embed_v1_en_5.5.1_3.0_1732743647389.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/nomic_embed_v1_en_5.5.1_3.0_1732743647389.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")
+
+embeddings = NomicEmbeddings.pretrained("nomic_embed_v1","en") \
+      .setInputCols(["document"]) \
+      .setOutputCol("embeddings")       
+
+pipeline = Pipeline().setStages([documentAssembler, embeddings])
+data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new DocumentAssembler() 
+    .setInputCol("text") 
+    .setOutputCol("document")
+
+val embeddings = NomicEmbeddings.pretrained("nomic_embed_v1","en") 
+    .setInputCols(Array("document")) 
+    .setOutputCol("embeddings")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, embeddings))
+val data = Seq("I love spark-nlp").toDF("text")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|nomic_embed_v1|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[generation]|
+|Language:|en|
+|Size:|255.0 MB|
+
+## References
+
+https://huggingface.co/nomic-ai/nomic-embed-text-v1
diff --git a/docs/_posts/ahmedlone127/2024-11-29-phi_3_mini_128k_instruct_en.md b/docs/_posts/ahmedlone127/2024-11-29-phi_3_mini_128k_instruct_en.md
@@ -0,0 +1,86 @@
+---
+layout: model
+title: phi_3_mini_128k_instruct model from microsoft
+author: John Snow Labs
+name: phi_3_mini_128k_instruct
+date: 2024-11-29
+tags: [en, open_source, openvino]
+task: Text Generation
+language: en
+edition: Spark NLP 5.5.1
+spark_version: 3.0
+supported: true
+engine: openvino
+annotator: Phi3Transformer
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained Phi3Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`phi_3_mini_128k_instruct` is a english model originally trained by openbmb.
+
+{:.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/phi_3_mini_128k_instruct_en_5.5.1_3.0_1732897700551.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/phi_3_mini_128k_instruct_en_5.5.1_3.0_1732897700551.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")
+
+seq2seq = Phi3Transformer.pretrained("phi_3_mini_128k_instruct","en") \
+      .setInputCols(["document"]) \
+      .setOutputCol("generation")       
+
+pipeline = Pipeline().setStages([documentAssembler, seq2seq])
+data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new DocumentAssembler() 
+    .setInputCol("text") 
+    .setOutputCol("document")
+
+val seq2seq = Phi3Transformer.pretrained("phi_3_mini_128k_instruct","en") 
+    .setInputCols(Array("document")) 
+    .setOutputCol("generation")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, seq2seq))
+val data = Seq("I love spark-nlp").toDF("text")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|phi_3_mini_128k_instruct|
+|Compatibility:|Spark NLP 5.5.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[generation]|
+|Language:|en|
+|Size:|3.5 GB|
+
+## References
+
+https://huggingface.co/microsoft/Phi-3-mini-128k-instruct