Skip to content

Commit

Permalink
Models hub (#13913)
Browse files Browse the repository at this point in the history 
---------

Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>

* 2023-06-27-roberta_embeddings_robertinh_gl (#13868)

* Add model 2023-06-27-roberta_embeddings_robertinh_gl

* Add model 2023-06-27-roberta_embeddings_roberta_base_wechsel_german_de

* Add model 2023-06-27-roberta_embeddings_roberta_base_russian_v0_ru

* Add model 2023-06-27-roberta_embeddings_ruperta_base_finetuned_spa_constitution_en

* Add model 2023-06-27-roberta_embeddings_robasqu_eu

* Add model 2023-06-27-roberta_embeddings_roberta_ko_small_ko

* Add model 2023-06-27-roberta_embeddings_hindi_hi

* Add model 2023-06-27-roberta_embeddings_sundanese_roberta_base_su

* Add model 2023-06-27-roberta_embeddings_roberta_pubmed_en

* Add model 2023-06-27-roberta_embeddings_distilroberta_base_climate_f_en

* Add model 2023-06-27-roberta_embeddings_roberta_urdu_small_ur

* Add model 2023-06-27-roberta_embeddings_BR_BERTo_pt

* Add model 2023-06-27-roberta_embeddings_distilroberta_base_climate_d_s_en

* Add model 2023-06-27-roberta_embeddings_distilroberta_base_climate_d_en

* Add model 2023-06-27-roberta_embeddings_ukr_roberta_base_uk

* Add model 2023-06-27-roberta_embeddings_roberta_base_wechsel_french_fr

* Add model 2023-06-27-roberta_embeddings_Bible_roberta_base_en

* Add model 2023-06-27-roberta_embeddings_bertin_roberta_large_spanish_es

* Add model 2023-06-27-roberta_embeddings_roberta_base_wechsel_chinese_zh

* Add model 2023-06-27-roberta_embeddings_bertin_roberta_base_spanish_es

* Add model 2023-06-27-roberta_embeddings_bertin_base_gaussian_es

* Add model 2023-06-27-roberta_embeddings_bertin_base_random_exp_512seqlen_es

* Add model 2023-06-27-roberta_embeddings_RuPERTa_base_es

* Add model 2023-06-27-roberta_embeddings_roberta_base_bne_es

* Add model 2023-06-27-roberta_embeddings_bertin_base_stepwise_exp_512seqlen_es

* Add model 2023-06-27-roberta_embeddings_MedRoBERTa.nl_nl

* Add model 2023-06-27-roberta_embeddings_bertin_base_random_es

* Add model 2023-06-27-roberta_embeddings_RoBERTalex_es

* Add model 2023-06-27-roberta_embeddings_SecRoBERTa_en

* Add model 2023-06-27-roberta_embeddings_KanBERTo_kn

* Add model 2023-06-27-roberta_embeddings_distilroberta_base_finetuned_jira_qt_issue_title_en

* Add model 2023-06-27-roberta_embeddings_MedRoBERTa.nl_nl

* Add model 2023-06-27-roberta_embeddings_distilroberta_base_finetuned_jira_qt_issue_titles_and_bodies_en

* Add model 2023-06-27-roberta_embeddings_bertin_base_stepwise_es

* Add model 2023-06-27-roberta_embeddings_KanBERTo_kn

* Add model 2023-06-27-roberta_embeddings_bertin_base_gaussian_exp_512seqlen_es

* Add model 2023-06-27-roberta_embeddings_mlm_spanish_roberta_base_es

* Add model 2023-06-27-roberta_embeddings_KNUBert_kn

* Add model 2023-06-27-roberta_embeddings_javanese_roberta_small_jv

* Add model 2023-06-27-roberta_embeddings_indonesian_roberta_base_id

* Add model 2023-06-27-roberta_embeddings_indic_transformers_hi_roberta_hi

* Add model 2023-06-27-roberta_embeddings_indo_roberta_small_id

* Add model 2023-06-27-roberta_embeddings_fairlex_scotus_minilm_en

* Add model 2023-06-27-roberta_embeddings_indic_transformers_te_roberta_te

* Add model 2023-06-27-roberta_embeddings_javanese_roberta_small_imdb_jv

* Add model 2023-06-27-roberta_embeddings_jurisbert_es

* Add model 2023-06-27-roberta_embeddings_roberta_base_indonesian_522M_id

* Add model 2023-06-27-roberta_embeddings_fairlex_ecthr_minilm_en

* Add model 2023-06-27-roberta_embeddings_muppet_roberta_base_en

---------

Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>

* Add model 2023-06-29-xlmroberta_embeddings_paraphrase_mpnet_base_v2_xx (#13872)

Co-authored-by: Damla-Gurbaz <dml.grbz.01@gmail.com>

* 2023-06-08-instructor_base_en (#13850)

* Add model 2023-06-08-instructor_base_en

* Update 2023-06-08-instructor_base_en.md

* Add model 2023-06-21-e5_base_v2_en

* Add model 2023-06-21-e5_base_en

* Add model 2023-06-21-e5_large_v2_en

* Add model 2023-06-21-e5_large_en

* Add model 2023-06-21-e5_small_v2_en

* Add model 2023-06-21-e5_small_en

* Add model 2023-06-21-instructor_large_en

---------

Co-authored-by: prabod <prabod@rathnayaka.me>
Co-authored-by: Maziyar Panahi <maziyar.panahi@iscpif.fr>

* 2023-06-28-roberta_base_en (#13871)

* Add model 2023-06-28-roberta_base_en

* Add model 2023-06-28-roberta_base_opt_en

* Add model 2023-06-28-roberta_base_quantized_en

* Add model 2023-06-28-small_bert_L2_768_en

* Add model 2023-06-28-small_bert_L2_768_opt_en

* Add model 2023-06-28-small_bert_L2_768_quantized_en

* Add model 2023-06-28-distilbert_base_cased_en

* Add model 2023-06-28-distilbert_base_cased_opt_en

* Add model 2023-06-28-distilbert_base_cased_quantized_en

* Add model 2023-06-28-deberta_v3_base_en

* Add model 2023-06-28-deberta_v3_base_opt_en

* Add model 2023-06-28-deberta_v3_base_quantized_en

* Add model 2023-06-28-distilbert_base_uncased_en

* Add model 2023-06-28-distilbert_base_uncased_opt_en

* Add model 2023-06-28-distilbert_base_uncased_quantized_en

* Add model 2023-06-28-distilbert_base_multilingual_cased_xx

* Add model 2023-06-28-distilbert_base_multilingual_cased_xx

* Add model 2023-06-28-distilbert_base_multilingual_cased_opt_xx

* Add model 2023-06-28-distilbert_base_multilingual_cased_quantized_xx

* Add model 2023-06-28-distilbert_embeddings_distilbert_base_german_cased_de

* Add model 2023-06-28-distilbert_embeddings_distilbert_base_german_cased_opt_de

* Add model 2023-06-28-distilbert_embeddings_distilbert_base_german_cased_quantized_de

* Add model 2023-06-29-bert_base_cased_en

* Add model 2023-06-29-bert_base_cased_opt_en

* Add model 2023-06-29-bert_base_cased_quantized_en

---------

Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>

* Add model 2023-07-05-image_classifier_convnext_tiny_224_local_en (#13879)

Co-authored-by: gadde5300 <gadde5300@gmail.com>

* Add model 2023-07-06-quora_distilbert_multilingual_en (#13882)

Co-authored-by: purulalwani <purulalwani@gmail.com>

* removed duplicated sections (#13885)

* Add model 2023-07-20-xlm_roberta_large_zero_shot_classifier_xnli_anli_xx (#13900)

Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>

* Add model 2023-07-28-twitter_xlm_roberta_base_sentiment_en (#13905)

Co-authored-by: veerdhwaj <veerdhwaj@aol.com>

* 2023-07-30-albert_embeddings_ALR_BERT_ro (#13910)

* Add model 2023-07-30-albert_embeddings_ALR_BERT_ro

* Add model 2023-07-30-albert_embeddings_albert_base_japanese_v1_ja

* Add model 2023-07-30-albert_embeddings_albert_large_arabic_ar

* Add model 2023-07-30-albert_embeddings_albert_fa_base_v2_fa

* Add model 2023-07-30-albert_embeddings_albert_german_ner_de

* Add model 2023-07-30-albert_embeddings_albert_fa_zwnj_base_v2_fa

* Add model 2023-07-30-albert_embeddings_marathi_albert_mr

* Add model 2023-07-30-albert_embeddings_albert_tiny_bahasa_cased_ms

* Add model 2023-07-30-albert_embeddings_albert_base_bahasa_cased_ms

* Add model 2023-07-30-albert_embeddings_fralbert_base_fr

* Add model 2023-07-30-albert_embeddings_marathi_albert_v2_mr

* Add model 2023-07-30-albert_embeddings_albert_base_arabic_ar

* Add model 2023-07-30-albert_embeddings_albert_large_bahasa_cased_ms

* Add model 2023-07-30-camembert_embeddings_das22_10_camembert_pretrained_fr

* Add model 2023-07-30-camembert_embeddings_zhenghuabin_generic_model_fr

* Add model 2023-07-30-camembert_embeddings_das22_10_camembert_pretrained_fr

* Add model 2023-07-30-camembert_embeddings_camembert_mlm_fr

* Add model 2023-07-30-camembert_embeddings_edge2992_generic_model_fr

* Add model 2023-07-30-camembert_embeddings_elusive_magnolia_generic_model_fr

* Add model 2023-07-30-camembert_embeddings_zhenghuabin_generic_model_fr

* Add model 2023-07-30-camembert_embeddings_camembert_aux_amandes_mt

* Add model 2023-07-30-camembert_embeddings_elliotsmith_generic_model_fr

* Add model 2023-07-30-camembert_embeddings_dianeshan_generic_model_fr

* fixed wrong version

* Add model 2023-07-31-camembert_embeddings_ankitkupadhyay_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_devtrent_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_eduardopds_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_adeiMousa_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_ericchchiu_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_Sebu_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_Weipeng_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_codingJacob_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_SummFinFR_fr

* Add model 2023-07-31-camembert_embeddings_MYX4567_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_Katster_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_MYX4567_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_JonathanSum_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_Leisa_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_adam1224_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_est_roberta_et

* Add model 2023-07-31-camembert_embeddings_generic2_fr

* Add model 2023-07-31-camembert_embeddings_ysharma_generic_model_2_fr

* Add model 2023-07-31-camembert_embeddings_DoyyingFace_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_Henrywang_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_xkang_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_wangst_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_seyfullah_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_tnagata_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_yancong_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_safik_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_tpanza_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_peterhsu_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_pgperrone_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_osanseviero_generic_model_fr

* Add model 2023-07-31-camembert_embeddings_lijingxin_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_kaushikacharya_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_new_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_mbateman_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_lijingxin_generic_model_2_fr

* Add model 2023-08-01-camembert_embeddings_katrin_kc_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_linyi_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_lewtun_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_joe8zhang_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_sloberta_sl

* Add model 2023-08-01-camembert_embeddings_generic_model_test_fr

* Add model 2023-08-01-camembert_embeddings_jcai1_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_umberto_commoncrawl_cased_v1_it

* Add model 2023-08-01-camembert_embeddings_DataikuNLP_camembert_base_fr

* Add model 2023-08-01-camembert_embeddings_umberto_wikipedia_uncased_v1_it

* Add model 2023-08-01-camembert_base_oscar_4gb_fr

* Add model 2023-08-01-camembert_embeddings_distilcamembert_base_fr

* Add model 2023-08-01-camembert_base_wikipedia_4gb_fr

* Add model 2023-08-01-camembert_base_ccnet_fr

* Add model 2023-08-01-camembert_base_oscar_4gb_fr

* Add model 2023-08-01-camembert_embeddings_hackertec_generic_fr

* Add model 2023-08-01-camembert_base_ccnet_fr

* Add model 2023-08-01-camembert_embeddings_h4d35_generic_model_fr

* Add model 2023-08-01-camembert_embeddings_bertweetfr_base_fr

* Add model 2023-08-01-camembert_base_ccnet_4gb_fr

* Add model 2023-08-01-camembert_base_ccnet_4gb_fr

* Add model 2023-08-01-xlmroberta_embeddings_fairlex_fscs_minilm_xx

* Add model 2023-08-01-xlmroberta_embeddings_fairlex_cail_minilm_zh

* Add model 2023-08-01-camembert_base_fr

* Add model 2023-08-01-camembert_base_opt_fr

* Add model 2023-08-01-camembert_base_quantized_fr

* Add model 2023-08-02-albert_base_uncased_en

* Add model 2023-08-02-albert_base_uncased_opt_en

* Add model 2023-08-02-albert_base_uncased_quantized_en

* Add model 2023-08-02-albert_large_uncased_en

* Add model 2023-08-02-albert_large_uncased_en

* Add model 2023-08-02-albert_large_uncased_opt_en

* Add model 2023-08-02-albert_large_uncased_quantized_en

---------

Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>

* 2023-07-28-twitter_xlm_roberta_base_sentiment_en (#13906)

* Add model 2023-07-28-twitter_xlm_roberta_base_sentiment_en

* Add model 2023-07-31-twitter_xlm_roberta_base_sentiment_pdc_en

* Add model 2023-07-31-sentiment_twitter_xlm_roBerta_pdc_en

---------

Co-authored-by: veerdhwaj <veerdhwaj@aol.com>

---------

Co-authored-by: jsl-models <74001263+jsl-models@users.noreply.github.com>
Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>
Co-authored-by: purulalwani <purulalwani@gmail.com>
Co-authored-by: veerdhwaj <veerdhwaj@aol.com>
  • Loading branch information
@maziyarpanahi @jsl-models
@ahmedlone127 @purulalwani @veerdhwaj
5 people authored Aug 2, 2023
1 parent 2b2f93c commit 35478e0
Show file tree
Hide file tree
Showing 88 changed files with 8,403 additions and 0 deletions.
106 changes: 106 additions & 0 deletions .../ahmedlone127/2023-07-20-xlm_roberta_large_zero_shot_classifier_xnli_anli_xx.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,106 @@
---
layout: model
title: XlmRoBertaZero-Shot Classification Large xlm_roberta_large_zero_shot_classifier_xnli_anli
author: John Snow Labs
name: xlm_roberta_large_zero_shot_classifier_xnli_anli
date: 2023-07-20
tags: [zero_shot, xx, open_source, tensorflow]
task: Zero-Shot Classification
language: xx
edition: Spark NLP 5.0.2
spark_version: 3.0
supported: true
engine: tensorflow
annotator: XlmRoBertaForZeroShotClassification
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

This model is intended to be used for zero-shot text classification, especially in English. It is fine-tuned on NLI by using XlmRoberta Large model.

XlmRoBertaForZeroShotClassificationusing a ModelForSequenceClassification trained on NLI (natural language inference) tasks. Equivalent of TFXLMRoBertaForZeroShotClassification models, but these models don’t require a hardcoded number of potential classes, they can be chosen at runtime. It usually means it’s slower but it is much more flexible.

We used TFXLMRobertaForSequenceClassification to train this model and used XlmRoBertaForZeroShotClassification annotator in Spark NLP 🚀 for prediction at scale!

## 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/xlm_roberta_large_zero_shot_classifier_xnli_anli_xx_5.0.2_3.0_1689886974932.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/xlm_roberta_large_zero_shot_classifier_xnli_anli_xx_5.0.2_3.0_1689886974932.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_assembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')

tokenizer = Tokenizer() \
.setInputCols(['document']) \
.setOutputCol('token')

zeroShotClassifier = XlmRobertaForSequenceClassification \
.pretrained('xlm_roberta_large_zero_shot_classifier_xnli_anli', 'xx') \
.setInputCols(['token', 'document']) \
.setOutputCol('class') \
.setCaseSensitive(True) \
.setMaxSentenceLength(512) \
.setCandidateLabels(["urgent", "mobile", "travel", "movie", "music", "sport", "weather", "technology"])

pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
zeroShotClassifier
])

example = spark.createDataFrame([['I have a problem with my iphone that needs to be resolved asap!!']]).toDF("text")
result = pipeline.fit(example).transform(example)

```
```scala
val document_assembler = DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")

val tokenizer = Tokenizer()
.setInputCols("document")
.setOutputCol("token")

val zeroShotClassifier = XlmRobertaForSequenceClassification.pretrained("xlm_roberta_large_zero_shot_classifier_xnli_anli", "xx")
.setInputCols("document", "token")
.setOutputCol("class")
.setCaseSensitive(true)
.setMaxSentenceLength(512)
.setCandidateLabels(Array("urgent", "mobile", "travel", "movie", "music", "sport", "weather", "technology"))

val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, zeroShotClassifier))
val example = Seq("I have a problem with my iphone that needs to be resolved asap!!").toDS.toDF("text")
val result = pipeline.fit(example).transform(example)
```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|xlm_roberta_large_zero_shot_classifier_xnli_anli|
|Compatibility:|Spark NLP 5.0.2+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[token, document]|
|Output Labels:|[label]|
|Language:|xx|
|Size:|2.0 GB|
|Case sensitive:|true|
99 changes: 99 additions & 0 deletions docs/_posts/ahmedlone127/2023-07-30-albert_embeddings_ALR_BERT_ro.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,99 @@
---
layout: model
title: Romanian ALBERT Embeddings (from dragosnicolae555)
author: John Snow Labs
name: albert_embeddings_ALR_BERT
date: 2023-07-30
tags: [albert, embeddings, ro, open_source, onnx]
task: Embeddings
language: ro
edition: Spark NLP 5.0.2
spark_version: 3.0
supported: true
engine: onnx
annotator: AlbertEmbeddings
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained ALBERT Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. `ALR_BERT` is a Romanian model orginally trained by `dragosnicolae555`.

## 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/albert_embeddings_ALR_BERT_ro_5.0.2_3.0_1690752767725.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/albert_embeddings_ALR_BERT_ro_5.0.2_3.0_1690752767725.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")

tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")

embeddings = AlbertEmbeddings.pretrained("albert_embeddings_ALR_BERT","ro") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")

pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["Îmi place Spark NLP"]]).toDF("text")

result = pipeline.fit(data).transform(data)
```
```scala
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")

val tokenizer = new Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")

val embeddings = AlbertEmbeddings.pretrained("albert_embeddings_ALR_BERT","ro")
.setInputCols(Array("document", "token"))
.setOutputCol("embeddings")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))

val data = Seq("Îmi place Spark NLP").toDF("text")

val result = pipeline.fit(data).transform(data)
```

{:.nlu-block}
```python
import nlu
nlu.load("ro.embed.ALR_BERT").predict("""Îmi place Spark NLP""")
```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|albert_embeddings_ALR_BERT|
|Compatibility:|Spark NLP 5.0.2+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[sentence, token]|
|Output Labels:|[bert]|
|Language:|ro|
|Size:|51.7 MB|
|Case sensitive:|false|
99 changes: 99 additions & 0 deletions docs/_posts/ahmedlone127/2023-07-30-albert_embeddings_albert_base_arabic_ar.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,99 @@
---
layout: model
title: Arabic ALBERT Embeddings (Base)
author: John Snow Labs
name: albert_embeddings_albert_base_arabic
date: 2023-07-30
tags: [albert, embeddings, ar, open_source, onnx]
task: Embeddings
language: ar
edition: Spark NLP 5.0.2
spark_version: 3.0
supported: true
engine: onnx
annotator: AlbertEmbeddings
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained ALBERT Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. `albert-base-arabic` is a Arabic model orginally trained by `asafaya`.

## 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/albert_embeddings_albert_base_arabic_ar_5.0.2_3.0_1690753212237.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/albert_embeddings_albert_base_arabic_ar_5.0.2_3.0_1690753212237.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")

tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")

embeddings = AlbertEmbeddings.pretrained("albert_embeddings_albert_base_arabic","ar") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")

pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["أنا أحب شرارة NLP"]]).toDF("text")

result = pipeline.fit(data).transform(data)
```
```scala
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")

val tokenizer = new Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")

val embeddings = AlbertEmbeddings.pretrained("albert_embeddings_albert_base_arabic","ar")
.setInputCols(Array("document", "token"))
.setOutputCol("embeddings")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))

val data = Seq("أنا أحب شرارة NLP").toDF("text")

val result = pipeline.fit(data).transform(data)
```

{:.nlu-block}
```python
import nlu
nlu.load("ar.embed.albert").predict("""أنا أحب شرارة NLP""")
```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|albert_embeddings_albert_base_arabic|
|Compatibility:|Spark NLP 5.0.2+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[sentence, token]|
|Output Labels:|[bert]|
|Language:|ar|
|Size:|42.0 MB|
|Case sensitive:|false|
Loading

0 comments on commit 35478e0

Please sign in to comment.