From 83faec9167d3010707d05d8676714e2f757598e2 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 07:11:53 +0700 Subject: [PATCH 01/12] Add model 2023-04-20-distilbert_base_uncased_mnli_en --- ...3-04-20-distilbert_base_uncased_mnli_en.md | 107 ++++++++++++++++++ 1 file changed, 107 insertions(+) create mode 100644 docs/_posts/ahmedlone127/2023-04-20-distilbert_base_uncased_mnli_en.md diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_uncased_mnli_en.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_uncased_mnli_en.md new file mode 100644 index 00000000000000..cdd5e856452338 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_uncased_mnli_en.md @@ -0,0 +1,107 @@ +--- +layout: model +title: DistilBERTZero-Shot Classification Base - MNLI(distilbert_base_uncased_mnli) +author: John Snow Labs +name: distilbert_base_uncased_mnli +date: 2023-04-20 +tags: [zero_shot, mnli, distilbert, base, english, en, oepn_source, open_source, tensorflow] +task: Zero-Shot Classification +language: en +edition: Spark NLP 4.4.1 +spark_version: [3.2, 3.0] +supported: true +engine: tensorflow +annotator: DistilBertForZeroShotClassification +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 MNLI by using DistilBERT Base Uncased model. + +DistilBertForZeroShotClassification using a ModelForSequenceClassification trained on NLI (natural language inference) tasks. Equivalent of DistilBertForSequenceClassification 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 TFDistilBertForSequenceClassification to train this model and used DistilBertForZeroShotClassification annotator in Spark NLP 🚀 for prediction at scale! + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mnli_en_4.4.1_3.2_1681949033641.zip){:.button.button-orange} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mnli_en_4.4.1_3.2_1681949033641.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +document_assembler = DocumentAssembler() \ +.setInputCol('text') \ +.setOutputCol('document') + +tokenizer = Tokenizer() \ +.setInputCols(['document']) \ +.setOutputCol('token') + +zeroShotClassifier = DistilBertForZeroShotClassification \ +.pretrained('distilbert_base_uncased_mnli', 'en') \ +.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 = DistilBertForZeroShotClassification.pretrained("distilbert_base_uncased_mnli", "en") +.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) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_mnli| +|Compatibility:|Spark NLP 4.4.1+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[token, document]| +|Output Labels:|[multi_class]| +|Language:|en| +|Size:|249.7 MB| +|Case sensitive:|true| \ No newline at end of file From 551d336987840d2e302a22351b0ae7006a923665 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 07:36:20 +0700 Subject: [PATCH 02/12] Add model 2023-04-20-distilbert_base_turkish_cased_allnli_tr --- ...distilbert_base_turkish_cased_allnli_tr.md | 107 ++++++++++++++++++ 1 file changed, 107 insertions(+) create mode 100644 docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_allnli_tr.md diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_allnli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_allnli_tr.md new file mode 100644 index 00000000000000..4ef3afd6b2d566 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_allnli_tr.md @@ -0,0 +1,107 @@ +--- +layout: model +title: DistilBERTZero-Shot Classification Base - distilbert_base_turkish_cased_allnli +author: John Snow Labs +name: distilbert_base_turkish_cased_allnli +date: 2023-04-20 +tags: [zero_shot, distilbert, base, tr, turkish, cased, open_source, tensorflow] +task: Zero-Shot Classification +language: tr +edition: Spark NLP 4.4.1 +spark_version: [3.2, 3.0] +supported: true +engine: tensorflow +annotator: DistilBertForZeroShotClassification +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 MNLI by using DistilBERT Base Uncased model. + +DistilBertForZeroShotClassification using a ModelForSequenceClassification trained on NLI (natural language inference) tasks. Equivalent of DistilBertForSequenceClassification 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 TFDistilBertForSequenceClassification to train this model and used DistilBertForZeroShotClassification annotator in Spark NLP 🚀 for prediction at scale! + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_allnli_tr_4.4.1_3.2_1681950583033.zip){:.button.button-orange} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_allnli_tr_4.4.1_3.2_1681950583033.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +document_assembler = DocumentAssembler() \ +.setInputCol('text') \ +.setOutputCol('document') + +tokenizer = Tokenizer() \ +.setInputCols(['document']) \ +.setOutputCol('token') + +zeroShotClassifier = DistilBertForZeroShotClassification \ +.pretrained('distilbert_base_turkish_cased_allnli', 'en') \ +.setInputCols(['token', 'document']) \ +.setOutputCol('class') \ +.setCaseSensitive(True) \ +.setMaxSentenceLength(512) \ +.setCandidateLabels(["olumsuz", "olumlu"]) + +pipeline = Pipeline(stages=[ +document_assembler, +tokenizer, +zeroShotClassifier +]) + +example = spark.createDataFrame([['Senaryo çok saçmaydı, beğendim diyemem.']]).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 = DistilBertForZeroShotClassification.pretrained("distilbert_base_turkish_cased_allnli", "en") +.setInputCols("document", "token") +.setOutputCol("class") +.setCaseSensitive(true) +.setMaxSentenceLength(512) +.setCandidateLabels(Array("olumsuz", "olumlu")) + +val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, zeroShotClassifier)) + +val example = Seq("Senaryo çok saçmaydı, beğendim diyemem.").toDS.toDF("text") + +val result = pipeline.fit(example).transform(example) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_turkish_cased_allnli| +|Compatibility:|Spark NLP 4.4.1+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[token, document]| +|Output Labels:|[multi_class]| +|Language:|tr| +|Size:|254.3 MB| +|Case sensitive:|true| \ No newline at end of file From fd5ed22e2497676564fa5b91c32d6cc1353b8243 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 07:48:39 +0700 Subject: [PATCH 03/12] Add model 2023-04-20-distilbert_base_turkish_cased_snli_tr --- ...0-distilbert_base_turkish_cased_snli_tr.md | 107 ++++++++++++++++++ 1 file changed, 107 insertions(+) create mode 100644 docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_snli_tr.md diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_snli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_snli_tr.md new file mode 100644 index 00000000000000..4e17b138e90b7a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_snli_tr.md @@ -0,0 +1,107 @@ +--- +layout: model +title: DistilBERTZero-Shot Classification Base - distilbert_base_turkish_cased_snli +author: John Snow Labs +name: distilbert_base_turkish_cased_snli +date: 2023-04-20 +tags: [zero_shot, tr, turkish, distilbert, base, cased, open_source, tensorflow] +task: Zero-Shot Classification +language: tr +edition: Spark NLP 4.4.1 +spark_version: [3.2, 3.0] +supported: true +engine: tensorflow +annotator: DistilBertForZeroShotClassification +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 MNLI by using DistilBERT Base Uncased model. + +DistilBertForZeroShotClassification using a ModelForSequenceClassification trained on NLI (natural language inference) tasks. Equivalent of DistilBertForSequenceClassification 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 TFDistilBertForSequenceClassification to train this model and used DistilBertForZeroShotClassification annotator in Spark NLP 🚀 for prediction at scale! + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_snli_tr_4.4.1_3.2_1681951486863.zip){:.button.button-orange} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_snli_tr_4.4.1_3.2_1681951486863.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +document_assembler = DocumentAssembler() \ +.setInputCol('text') \ +.setOutputCol('document') + +tokenizer = Tokenizer() \ +.setInputCols(['document']) \ +.setOutputCol('token') + +zeroShotClassifier = DistilBertForZeroShotClassification \ +.pretrained('distilbert_base_turkish_cased_allnli', 'en') \ +.setInputCols(['token', 'document']) \ +.setOutputCol('class') \ +.setCaseSensitive(True) \ +.setMaxSentenceLength(512) \ +.setCandidateLabels(["olumsuz", "olumlu"]) + +pipeline = Pipeline(stages=[ +document_assembler, +tokenizer, +zeroShotClassifier +]) + +example = spark.createDataFrame([['Senaryo çok saçmaydı, beğendim diyemem.']]).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 = DistilBertForZeroShotClassification.pretrained("distilbert_base_turkish_cased_allnli", "en") +.setInputCols("document", "token") +.setOutputCol("class") +.setCaseSensitive(true) +.setMaxSentenceLength(512) +.setCandidateLabels(Array("olumsuz", "olumlu")) + +val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, zeroShotClassifier)) + +val example = Seq("Senaryo çok saçmaydı, beğendim diyemem.").toDS.toDF("text") + +val result = pipeline.fit(example).transform(example) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_turkish_cased_snli| +|Compatibility:|Spark NLP 4.4.1+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[token, document]| +|Output Labels:|[multi_class]| +|Language:|tr| +|Size:|254.3 MB| +|Case sensitive:|true| \ No newline at end of file From b9f64acdc92112d6e4e3c1aa8a04368e08dbdc55 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 08:02:11 +0700 Subject: [PATCH 04/12] Add model 2023-04-20-distilbert_base_turkish_cased_multinli_tr --- ...stilbert_base_turkish_cased_multinli_tr.md | 108 ++++++++++++++++++ 1 file changed, 108 insertions(+) create mode 100644 docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_multinli_tr.md diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_multinli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_multinli_tr.md new file mode 100644 index 00000000000000..4292e0722c832b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_multinli_tr.md @@ -0,0 +1,108 @@ +--- +layout: model +title: DistilBERTZero-Shot Classification Base - distilbert_base_turkish_cased_multinli +author: John Snow Labs +name: distilbert_base_turkish_cased_multinli +date: 2023-04-20 +tags: [zero_shot, tr, turkish, distilbert, base, cased, open_source, tensorflow] +task: Zero-Shot Classification +language: tr +edition: Spark NLP 4.4.1 +spark_version: [3.2, 3.0] +supported: true +engine: tensorflow +annotator: DistilBertForZeroShotClassification +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 MNLI by using DistilBERT Base Uncased model. + +DistilBertForZeroShotClassification using a ModelForSequenceClassification trained on NLI (natural language inference) tasks. Equivalent of DistilBertForSequenceClassification 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 TFDistilBertForSequenceClassification to train this model and used DistilBertForZeroShotClassification annotator in Spark NLP 🚀 for prediction at scale! + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_multinli_tr_4.4.1_3.2_1681952299918.zip){:.button.button-orange} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_multinli_tr_4.4.1_3.2_1681952299918.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +document_assembler = DocumentAssembler() \ +.setInputCol('text') \ +.setOutputCol('document') + +tokenizer = Tokenizer() \ +.setInputCols(['document']) \ +.setOutputCol('token') + +zeroShotClassifier = DistilBertForZeroShotClassification \ +.pretrained('distilbert_base_turkish_cased_allnli', 'en') \ +.setInputCols(['token', 'document']) \ +.setOutputCol('class') \ +.setCaseSensitive(True) \ +.setMaxSentenceLength(512) \ +.setCandidateLabels(["ekonomi", "siyaset","spor"]) + +pipeline = Pipeline(stages=[ +document_assembler, +tokenizer, +zeroShotClassifier +]) + +example = spark.createDataFrame([['Dolar yükselmeye devam ediyor.']]).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 = DistilBertForZeroShotClassification.pretrained("distilbert_base_turkish_cased_allnli", "en") +.setInputCols("document", "token") +.setOutputCol("class") +.setCaseSensitive(true) +.setMaxSentenceLength(512) +.setCandidateLabels(Array("ekonomi", "siyaset","spor")) + +val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, zeroShotClassifier)) + +val example = Seq("Dolar yükselmeye devam ediyor.").toDS.toDF("text") + +val result = pipeline.fit(example).transform(example) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_turkish_cased_multinli| +|Compatibility:|Spark NLP 4.4.1+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[token, document]| +|Output Labels:|[multi_class]| +|Language:|tr| +|Size:|254.3 MB| +|Case sensitive:|true| \ No newline at end of file From 6a1970ab8c128ba0b7083d8095082d695d37f41b Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 15:46:19 +0500 Subject: [PATCH 05/12] Update and rename 2023-04-20-distilbert_base_turkish_cased_allnli_tr.md to 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md --- ...o_shot_classifier_turkish_cased_allnli_tr.md} | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) rename docs/_posts/ahmedlone127/{2023-04-20-distilbert_base_turkish_cased_allnli_tr.md => 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md} (82%) diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_allnli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md similarity index 82% rename from docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_allnli_tr.md rename to docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md index 4ef3afd6b2d566..339231b9c921ce 100644 --- a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_allnli_tr.md +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md @@ -1,8 +1,8 @@ --- layout: model -title: DistilBERTZero-Shot Classification Base - distilbert_base_turkish_cased_allnli +title: DistilBERTZero-Shot Classification Base - distilbert_base_zero_shot_classifier_turkish_cased_allnli author: John Snow Labs -name: distilbert_base_turkish_cased_allnli +name: distilbert_base_zero_shot_classifier_turkish_cased_allnli date: 2023-04-20 tags: [zero_shot, distilbert, base, tr, turkish, cased, open_source, tensorflow] task: Zero-Shot Classification @@ -32,8 +32,8 @@ We used TFDistilBertForSequenceClassification to train this model and used Disti {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_allnli_tr_4.4.1_3.2_1681950583033.zip){:.button.button-orange} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_allnli_tr_4.4.1_3.2_1681950583033.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_zero_shot_classifier_turkish_cased_allnli_4.4.1_3.2_1681950583033.zip){:.button.button-orange} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr_4.4.1_3.2_1681950583033.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use @@ -51,7 +51,7 @@ tokenizer = Tokenizer() \ .setOutputCol('token') zeroShotClassifier = DistilBertForZeroShotClassification \ -.pretrained('distilbert_base_turkish_cased_allnli', 'en') \ +.pretrained('distilbert_base_zero_shot_classifier_turkish_cased_allnli', 'en') \ .setInputCols(['token', 'document']) \ .setOutputCol('class') \ .setCaseSensitive(True) \ @@ -76,7 +76,7 @@ val tokenizer = Tokenizer() .setInputCols("document") .setOutputCol("token") -val zeroShotClassifier = DistilBertForZeroShotClassification.pretrained("distilbert_base_turkish_cased_allnli", "en") +val zeroShotClassifier = DistilBertForZeroShotClassification.pretrained("distilbert_base_zero_shot_classifier_turkish_cased_allnli", "en") .setInputCols("document", "token") .setOutputCol("class") .setCaseSensitive(true) @@ -96,7 +96,7 @@ val result = pipeline.fit(example).transform(example) {:.table-model} |---|---| -|Model Name:|distilbert_base_turkish_cased_allnli| +|Model Name:|distilbert_base_zero_shot_classifier_turkish_cased_allnli| |Compatibility:|Spark NLP 4.4.1+| |License:|Open Source| |Edition:|Official| @@ -104,4 +104,4 @@ val result = pipeline.fit(example).transform(example) |Output Labels:|[multi_class]| |Language:|tr| |Size:|254.3 MB| -|Case sensitive:|true| \ No newline at end of file +|Case sensitive:|true| From 149e89374d2e8038462fb96eb3fb3a836df104b0 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 15:48:08 +0500 Subject: [PATCH 06/12] Update and rename 2023-04-20-distilbert_base_turkish_cased_multinli_tr.md to 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md --- ...shot_classifier_turkish_cased_multinli_tr.md} | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) rename docs/_posts/ahmedlone127/{2023-04-20-distilbert_base_turkish_cased_multinli_tr.md => 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md} (82%) diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_multinli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md similarity index 82% rename from docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_multinli_tr.md rename to docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md index 4292e0722c832b..18498912ee4fe5 100644 --- a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_multinli_tr.md +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md @@ -1,8 +1,8 @@ --- layout: model -title: DistilBERTZero-Shot Classification Base - distilbert_base_turkish_cased_multinli +title: DistilBERTZero-Shot Classification Base - distilbert_base_zero_shot_classifier_turkish_cased_multinli author: John Snow Labs -name: distilbert_base_turkish_cased_multinli +name: distilbert_base_zero_shot_classifier_turkish_cased_multinli date: 2023-04-20 tags: [zero_shot, tr, turkish, distilbert, base, cased, open_source, tensorflow] task: Zero-Shot Classification @@ -32,8 +32,8 @@ We used TFDistilBertForSequenceClassification to train this model and used Disti {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_multinli_tr_4.4.1_3.2_1681952299918.zip){:.button.button-orange} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_multinli_tr_4.4.1_3.2_1681952299918.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr_4.4.1_3.2_1681952299918.zip){:.button.button-orange} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr_4.4.1_3.2_1681952299918.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use @@ -51,7 +51,7 @@ tokenizer = Tokenizer() \ .setOutputCol('token') zeroShotClassifier = DistilBertForZeroShotClassification \ -.pretrained('distilbert_base_turkish_cased_allnli', 'en') \ +.pretrained('distilbert_base_zero_shot_classifier_turkish_cased_multinli', 'en') \ .setInputCols(['token', 'document']) \ .setOutputCol('class') \ .setCaseSensitive(True) \ @@ -77,7 +77,7 @@ val tokenizer = Tokenizer() .setInputCols("document") .setOutputCol("token") -val zeroShotClassifier = DistilBertForZeroShotClassification.pretrained("distilbert_base_turkish_cased_allnli", "en") +val zeroShotClassifier = DistilBertForZeroShotClassification.pretrained("distilbert_base_zero_shot_classifier_turkish_cased_multinli", "en") .setInputCols("document", "token") .setOutputCol("class") .setCaseSensitive(true) @@ -97,7 +97,7 @@ val result = pipeline.fit(example).transform(example) {:.table-model} |---|---| -|Model Name:|distilbert_base_turkish_cased_multinli| +|Model Name:|distilbert_base_zero_shot_classifier_turkish_cased_multinli| |Compatibility:|Spark NLP 4.4.1+| |License:|Open Source| |Edition:|Official| @@ -105,4 +105,4 @@ val result = pipeline.fit(example).transform(example) |Output Labels:|[multi_class]| |Language:|tr| |Size:|254.3 MB| -|Case sensitive:|true| \ No newline at end of file +|Case sensitive:|true| From 5625453d770973f902db685f337b552768b82e78 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 15:49:54 +0500 Subject: [PATCH 07/12] Update and rename 2023-04-20-distilbert_base_turkish_cased_snli_tr.md to 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md --- ...ero_shot_classifier_turkish_cased_snli_tr.md} | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) rename docs/_posts/ahmedlone127/{2023-04-20-distilbert_base_turkish_cased_snli_tr.md => 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md} (83%) diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_snli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md similarity index 83% rename from docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_snli_tr.md rename to docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md index 4e17b138e90b7a..b5cc2b12e6ae5c 100644 --- a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_turkish_cased_snli_tr.md +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md @@ -1,8 +1,8 @@ --- layout: model -title: DistilBERTZero-Shot Classification Base - distilbert_base_turkish_cased_snli +title: DistilBERTZero-Shot Classification Base - distilbert_base_zero_shot_classifier_turkish_cased_snli author: John Snow Labs -name: distilbert_base_turkish_cased_snli +name: distilbert_base_zero_shot_classifier_turkish_cased_snli date: 2023-04-20 tags: [zero_shot, tr, turkish, distilbert, base, cased, open_source, tensorflow] task: Zero-Shot Classification @@ -32,8 +32,8 @@ We used TFDistilBertForSequenceClassification to train this model and used Disti {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_snli_tr_4.4.1_3.2_1681951486863.zip){:.button.button-orange} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_snli_tr_4.4.1_3.2_1681951486863.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_zero_shot_classifier_turkish_cased_snli_tr_4.4.1_3.2_1681951486863.zip){:.button.button-orange} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_zero_shot_classifier_turkish_cased_snli_tr_4.4.1_3.2_1681951486863.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use @@ -51,7 +51,7 @@ tokenizer = Tokenizer() \ .setOutputCol('token') zeroShotClassifier = DistilBertForZeroShotClassification \ -.pretrained('distilbert_base_turkish_cased_allnli', 'en') \ +.pretrained('distilbert_base_zero_shot_classifier_turkish_cased_snli', 'en') \ .setInputCols(['token', 'document']) \ .setOutputCol('class') \ .setCaseSensitive(True) \ @@ -76,7 +76,7 @@ val tokenizer = Tokenizer() .setInputCols("document") .setOutputCol("token") -val zeroShotClassifier = DistilBertForZeroShotClassification.pretrained("distilbert_base_turkish_cased_allnli", "en") +val zeroShotClassifier = DistilBertForZeroShotClassification.pretrained("distilbert_base_zero_shot_classifier_turkish_cased_snli", "en") .setInputCols("document", "token") .setOutputCol("class") .setCaseSensitive(true) @@ -96,7 +96,7 @@ val result = pipeline.fit(example).transform(example) {:.table-model} |---|---| -|Model Name:|distilbert_base_turkish_cased_snli| +|Model Name:|distilbert_base_zero_shot_classifier_turkish_cased_snli| |Compatibility:|Spark NLP 4.4.1+| |License:|Open Source| |Edition:|Official| @@ -104,4 +104,4 @@ val result = pipeline.fit(example).transform(example) |Output Labels:|[multi_class]| |Language:|tr| |Size:|254.3 MB| -|Case sensitive:|true| \ No newline at end of file +|Case sensitive:|true| From d633b75b77303200ef4f30f15d0a410d1489d739 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 15:52:14 +0500 Subject: [PATCH 08/12] Update and rename 2023-04-20-distilbert_base_uncased_mnli_en.md to distilbert_base_zero_shot_classifier_turkish_cased_snli --- ...base_zero_shot_classifier_turkish_cased_snli} | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) rename docs/_posts/ahmedlone127/{2023-04-20-distilbert_base_uncased_mnli_en.md => distilbert_base_zero_shot_classifier_turkish_cased_snli} (84%) diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_uncased_mnli_en.md b/docs/_posts/ahmedlone127/distilbert_base_zero_shot_classifier_turkish_cased_snli similarity index 84% rename from docs/_posts/ahmedlone127/2023-04-20-distilbert_base_uncased_mnli_en.md rename to docs/_posts/ahmedlone127/distilbert_base_zero_shot_classifier_turkish_cased_snli index cdd5e856452338..10122f3d1afd6d 100644 --- a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_uncased_mnli_en.md +++ b/docs/_posts/ahmedlone127/distilbert_base_zero_shot_classifier_turkish_cased_snli @@ -1,8 +1,8 @@ --- layout: model -title: DistilBERTZero-Shot Classification Base - MNLI(distilbert_base_uncased_mnli) +title: DistilBERTZero-Shot Classification Base - MNLI(distilbert_base_zero_shot_classifier_uncased_mnli) author: John Snow Labs -name: distilbert_base_uncased_mnli +name: distilbert_base_zero_shot_classifier_uncased_mnli date: 2023-04-20 tags: [zero_shot, mnli, distilbert, base, english, en, oepn_source, open_source, tensorflow] task: Zero-Shot Classification @@ -32,8 +32,8 @@ We used TFDistilBertForSequenceClassification to train this model and used Disti {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mnli_en_4.4.1_3.2_1681949033641.zip){:.button.button-orange} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mnli_en_4.4.1_3.2_1681949033641.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_zero_shot_classifier_uncased_mnli_en_4.4.1_3.2_1681949033641.zip){:.button.button-orange} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_zero_shot_classifier_uncased_mnli_en_4.4.1_3.2_1681949033641.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use @@ -51,7 +51,7 @@ tokenizer = Tokenizer() \ .setOutputCol('token') zeroShotClassifier = DistilBertForZeroShotClassification \ -.pretrained('distilbert_base_uncased_mnli', 'en') \ +.pretrained('distilbert_base_zero_shot_classifier_uncased_mnli', 'en') \ .setInputCols(['token', 'document']) \ .setOutputCol('class') \ .setCaseSensitive(True) \ @@ -76,7 +76,7 @@ val tokenizer = Tokenizer() .setInputCols("document") .setOutputCol("token") -val zeroShotClassifier = DistilBertForZeroShotClassification.pretrained("distilbert_base_uncased_mnli", "en") +val zeroShotClassifier = DistilBertForZeroShotClassification.pretrained("distilbert_base_zero_shot_classifier_uncased_mnli", "en") .setInputCols("document", "token") .setOutputCol("class") .setCaseSensitive(true) @@ -96,7 +96,7 @@ val result = pipeline.fit(example).transform(example) {:.table-model} |---|---| -|Model Name:|distilbert_base_uncased_mnli| +|Model Name:|distilbert_base_zero_shot_classifier_uncased_mnli| |Compatibility:|Spark NLP 4.4.1+| |License:|Open Source| |Edition:|Official| @@ -104,4 +104,4 @@ val result = pipeline.fit(example).transform(example) |Output Labels:|[multi_class]| |Language:|en| |Size:|249.7 MB| -|Case sensitive:|true| \ No newline at end of file +|Case sensitive:|true| From b82b7d21c72e4297624167f232153afd24fa8822 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 15:54:26 +0500 Subject: [PATCH 09/12] Rename distilbert_base_zero_shot_classifier_turkish_cased_snli to distilbert_base_zero_shot_classifier_turkish_cased_snli_en.md --- ...distilbert_base_zero_shot_classifier_turkish_cased_snli_en.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/_posts/ahmedlone127/{distilbert_base_zero_shot_classifier_turkish_cased_snli => distilbert_base_zero_shot_classifier_turkish_cased_snli_en.md} (100%) diff --git a/docs/_posts/ahmedlone127/distilbert_base_zero_shot_classifier_turkish_cased_snli b/docs/_posts/ahmedlone127/distilbert_base_zero_shot_classifier_turkish_cased_snli_en.md similarity index 100% rename from docs/_posts/ahmedlone127/distilbert_base_zero_shot_classifier_turkish_cased_snli rename to docs/_posts/ahmedlone127/distilbert_base_zero_shot_classifier_turkish_cased_snli_en.md From f4f7f348ef8ab82aa42ac43c1773f3b45b67629e Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 15:55:10 +0500 Subject: [PATCH 10/12] Update 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md --- ...istilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md index b5cc2b12e6ae5c..63840286509e53 100644 --- a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_snli_tr.md @@ -19,7 +19,7 @@ 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 MNLI by using DistilBERT Base Uncased model. +This model is intended to be used for zero-shot text classification, especially in Trukish. It is fine-tuned on MNLI by using DistilBERT Base Uncased model. DistilBertForZeroShotClassification using a ModelForSequenceClassification trained on NLI (natural language inference) tasks. Equivalent of DistilBertForSequenceClassification 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. From 3f3c9774bfa9cd40aee8a4d719467895230c9c01 Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 15:55:12 +0500 Subject: [PATCH 11/12] Update 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md --- ...lbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md index 18498912ee4fe5..eb05ea476bc5a4 100644 --- a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_multinli_tr.md @@ -19,7 +19,7 @@ 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 MNLI by using DistilBERT Base Uncased model. +This model is intended to be used for zero-shot text classification, especially in Trukish. It is fine-tuned on MNLI by using DistilBERT Base Uncased model. DistilBertForZeroShotClassification using a ModelForSequenceClassification trained on NLI (natural language inference) tasks. Equivalent of DistilBertForSequenceClassification 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. From 3c1a20e7aea064a92ad5194843ff462d37a7f34f Mon Sep 17 00:00:00 2001 From: ahmedlone127 Date: Thu, 20 Apr 2023 15:55:15 +0500 Subject: [PATCH 12/12] Update 2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md --- ...tilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md index 339231b9c921ce..6d378879613f22 100644 --- a/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md +++ b/docs/_posts/ahmedlone127/2023-04-20-distilbert_base_zero_shot_classifier_turkish_cased_allnli_tr.md @@ -19,7 +19,7 @@ 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 MNLI by using DistilBERT Base Uncased model. +This model is intended to be used for zero-shot text classification, especially in Trukish. It is fine-tuned on MNLI by using DistilBERT Base Uncased model. DistilBertForZeroShotClassification using a ModelForSequenceClassification trained on NLI (natural language inference) tasks. Equivalent of DistilBertForSequenceClassification 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.