Skip to content

Commit

Permalink
2024-08-17-long_t5lephone_5000_en (#14371)
Browse files Browse the repository at this point in the history 
* Add model 2024-08-20-flan_t5_base_analogy_conceptnet_pipeline_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_spanish_tofunumber1_en

* Add model 2024-08-20-t5_base_tweetsumm_seed55_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_spanish_tofunumber1_pipeline_en

* Add model 2024-08-20-mt5_base_multi_label_czech_iiib_cs

* Add model 2024-08-20-english_vietnamese_envit5_base_news_train_pipeline_en

* Add model 2024-08-20-english_vietnamese_envit5_base_news_train_en

* Add model 2024-08-20-mt5_base_multi_label_czech_iiib_pipeline_cs

* Add model 2024-08-20-mt5_base_jaquad_qg_trimmed_120000_en

* Add model 2024-08-20-mt5_base_jaquad_qg_trimmed_120000_pipeline_en

* Add model 2024-08-20-mt5_small_3task_highlight_tquad2_tr

* Add model 2024-08-20-mt5_small_3task_highlight_tquad2_pipeline_tr

* Add model 2024-08-20-t5large_imdb_style_2_en

* Add model 2024-08-20-catt5_solr_finetunned_complet2_en

* Add model 2024-08-20-t5large_imdb_style_2_pipeline_en

* Add model 2024-08-20-catt5_solr_finetunned_complet2_pipeline_en

* Add model 2024-08-20-mt5_small_malayalam_10k_en

* Add model 2024-08-20-mt5_small_malayalam_10k_pipeline_en

* Add model 2024-08-20-turkmen_instruct_squad_large_en

* Add model 2024-08-20-shuffled_nodes_augmented_graphs_without_edge_document_level_t5_run1_en

* Add model 2024-08-20-shuffled_nodes_augmented_graphs_without_edge_document_level_t5_run1_pipeline_en

* Add model 2024-08-20-t5_60m_poli_aff_2020_10_en

* Add model 2024-08-20-t5_60m_poli_aff_2020_10_pipeline_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_german_yuvscherbatov_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_german_yuvscherbatov_pipeline_en

* Add model 2024-08-20-afrimt5_english_swahili_macrolanguage_news_en

* Add model 2024-08-20-afrimt5_english_swahili_macrolanguage_news_pipeline_en

* Add model 2024-08-20-kltn_coqe_vit5_total_aspol_v3_en

* Add model 2024-08-20-mt5_small_finetuned_multihead_230209_test3_en

* Add model 2024-08-20-kltn_coqe_vit5_total_aspol_v3_pipeline_en

* Add model 2024-08-20-t5_small_finetuned_wikisql_averagenlpenjoyer_en

* Add model 2024-08-20-t5_small_finetuned_wikisql_averagenlpenjoyer_pipeline_en

* Add model 2024-08-20-panl_sql_en

* Add model 2024-08-20-t5_small_few_shot_k_16_finetuned_squad_seed_0_pipeline_en

* Add model 2024-08-20-worknewt5en_tonga_tonga_islands_bn2_pipeline_en

* Add model 2024-08-20-t5_small_few_shot_k_16_finetuned_squad_seed_0_en

* Add model 2024-08-20-scifive_base_pubmed_pmc_finetuned_scifive_base_pubmed_pmc_pipeline_en

* Add model 2024-08-20-cnn_aligned_smallt5_cont2_en

* Add model 2024-08-20-mt5_small_finetuned_multihead_230209_test3_pipeline_en

* Add model 2024-08-20-practical_nlp_course_6_en

* Add model 2024-08-20-practical_nlp_course_6_pipeline_en

* Add model 2024-08-20-retrained_en

* Add model 2024-08-20-20240213_3_pipeline_en

* Add model 2024-08-20-cnn_aligned_smallt5_cont2_pipeline_en

* Add model 2024-08-20-t5_60m_poli_aff_2017_5_en

* Add model 2024-08-20-worknewt5en_tonga_tonga_islands_bn2_en

* Add model 2024-08-20-t5_60m_poli_aff_2017_5_pipeline_en

* Add model 2024-08-20-20240213_3_en

* Add model 2024-08-20-retrained_pipeline_en

* Add model 2024-08-20-scifive_base_pubmed_pmc_finetuned_scifive_base_pubmed_pmc_en

* Add model 2024-08-20-lite_llm_248_pipeline_en

* Add model 2024-08-20-lite_llm_248_en

* Add model 2024-08-20-panl_sql_pipeline_en

* Add model 2024-08-20-cs505_coqe_vit5_train_instructionn4_soapl_v1_en

* Add model 2024-08-20-mt5_base_trimmed_italian_75000_en

* Add model 2024-08-20-cs505_coqe_vit5_train_instructionn4_soapl_v1_pipeline_en

* Add model 2024-08-20-mt5_base_trimmed_italian_75000_pipeline_en

* Add model 2024-08-20-t5large_sst2_syntactic_adv_instruction_0_en

* Add model 2024-08-20-nlp_a3_2c_trained_en

* Add model 2024-08-20-mt5_small_nc16_400_deen_en

* Add model 2024-08-20-t5large_sst2_syntactic_adv_instruction_0_pipeline_en

* Add model 2024-08-20-banglat5_finetuned_headlinebt5_1000_en

* Add model 2024-08-20-banglat5_finetuned_headlinebt5_1000_pipeline_en

* Add model 2024-08-20-mt5_small_nc16_400_deen_pipeline_en

* Add model 2024-08-20-mt5_small_trimmed_italian_en

* Add model 2024-08-20-mt5_small_finetuned_english_tonga_tonga_islands_korean_101_en

* Add model 2024-08-20-nlp_a3_2c_trained_pipeline_en

* Add model 2024-08-20-mt5_small_trimmed_italian_pipeline_en

* Add model 2024-08-20-mt5_small_finetuned_english_tonga_tonga_islands_korean_101_pipeline_en

* Add model 2024-08-20-t5_tiny_random_length_96_learning_rate_0_0001_weight_decay_0_01_finetu_truncated_5e15da_en

* Add model 2024-08-20-t5_tiny_random_length_96_learning_rate_0_0001_weight_decay_0_01_finetu_truncated_5e15da_pipeline_en

* Add model 2024-08-20-t5_for_translation_roval15_en

* Add model 2024-08-20-t5_for_translation_roval15_pipeline_en

* Add model 2024-08-20-test_t5_small_example_kaggle2_en

* Add model 2024-08-20-test_t5_small_example_kaggle2_pipeline_en

* Add model 2024-08-20-t5_small_finetuned16_english_tonga_tonga_islands_german_en

* Add model 2024-08-20-t5_small_finetuned16_english_tonga_tonga_islands_german_pipeline_en

* Add model 2024-08-20-happy_transformer_t5_base_grammar_correction_lr_v3_en

* Add model 2024-08-20-happy_transformer_t5_base_grammar_correction_lr_v3_pipeline_en

* Add model 2024-08-20-flan_t5_small_finetuned_coqa_v0_6_en

* Add model 2024-08-20-flan_t5_small_finetuned_coqa_v0_6_pipeline_en

* Add model 2024-08-20-t5_base_few_shot_k_128_finetuned_squad_infilling_seed_2_en

* Add model 2024-08-20-t5_base_few_shot_k_128_finetuned_squad_infilling_seed_2_pipeline_en

* Add model 2024-08-20-slavic_t5_base_xx

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_spanish_whatdhack_en

* Add model 2024-08-20-slavic_t5_base_pipeline_xx

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_spanish_whatdhack_pipeline_en

* Add model 2024-08-20-all_mt5_base_15_wikisql_norwegian_sch_en

* Add model 2024-08-20-t5_60m_lm_wmt_2015_0_en

* Add model 2024-08-20-t5_60m_lm_wmt_2015_0_pipeline_en

* Add model 2024-08-20-lat_long_1_en

* Add model 2024-08-20-lat_long_1_pipeline_en

* Add model 2024-08-20-qg_supercat666_en

* Add model 2024-08-20-all_mt5_base_15_wikisql_norwegian_sch_pipeline_en

* Add model 2024-08-20-qg_supercat666_pipeline_en

* Add model 2024-08-20-t5_base_bt2_khanq_eduqg_en

* Add model 2024-08-20-t5_base_bt2_khanq_eduqg_pipeline_en

* Add model 2024-08-20-mt5_small_sport_en

* Add model 2024-08-20-mt5_small_english_10k_en

* Add model 2024-08-20-real_prompt_100_500sync_all_gen_t5_small_pipeline_en

* Add model 2024-08-20-mt5_small_sport_pipeline_en

* Add model 2024-08-20-cs505_coqe_vit5_total_instruction0_sapol_v1_h1_pipeline_en

* Add model 2024-08-20-cs505_coqe_vit5_total_instruction0_sapol_v1_h1_en

* Add model 2024-08-20-real_prompt_100_500sync_all_gen_t5_small_en

* Add model 2024-08-20-mt5_small_english_10k_pipeline_en

* Add model 2024-08-20-question_model_t5_tokenizer_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_spanish_erfangc_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_spanish_erfangc_pipeline_en

* Add model 2024-08-20-question_model_t5_tokenizer_pipeline_en

* Add model 2024-08-20-t5doctalk_en

* Add model 2024-08-20-t5doctalk_pipeline_en

* Add model 2024-08-20-t5_small_finetuned_xsum_hugginfacexf_en

* Add model 2024-08-20-t5_small_finetuned_xsum_hugginfacexf_pipeline_en

* Add model 2024-08-20-t5_russian_finetuned_en

* Add model 2024-08-20-t5_russian_finetuned_pipeline_en

* Add model 2024-08-20-mt5_small_trimmed_korean_10000_koquad_qa_ko

* Add model 2024-08-20-mt5_small_trimmed_korean_10000_koquad_qa_pipeline_ko

* Add model 2024-08-20-t5_ultradetox_en

* Add model 2024-08-20-t5_ultradetox_pipeline_en

* Add model 2024-08-20-mt5_base_coba_coba_coba_en

* Add model 2024-08-20-t5large_tweet_emotion_flip_instruction_2_en

* Add model 2024-08-20-mt5_base_coba_coba_coba_pipeline_en

* Add model 2024-08-20-t5large_tweet_emotion_flip_instruction_2_pipeline_en

* Add model 2024-08-20-bikes_t5_small_12_en

* Add model 2024-08-20-bikes_t5_small_12_pipeline_en

* Add model 2024-08-20-distilled_mt5_small_0_4_2_en

* Add model 2024-08-20-distilled_mt5_small_0_4_2_pipeline_en

* Add model 2024-08-20-t5_base_bt1_khanq_eduqg_en

* Add model 2024-08-20-t5_base_bt1_khanq_eduqg_pipeline_en

* Add model 2024-08-20-t5_small_squad_newsqa_qag_trained_en

* Add model 2024-08-20-t5_small_squad_newsqa_qag_trained_pipeline_en

* Add model 2024-08-20-russian_t5_comments_sum_en

* Add model 2024-08-20-russian_t5_comments_sum_pipeline_en

* Add model 2024-08-20-t5_slovene_large_oasst_pairs_en

* Add model 2024-08-20-t5_slovene_large_oasst_pairs_pipeline_en

* Add model 2024-08-20-t5_60m_lm_wmt_2018_10_en

* Add model 2024-08-20-t5_60m_lm_wmt_2018_10_pipeline_en

* Add model 2024-08-20-mt5_small_squad_qa_trimmed_english_10000_en

* Add model 2024-08-20-mt5_base_zhquad_qg_zh

* Add model 2024-08-20-mt5_small_squad_qa_trimmed_english_10000_pipeline_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_szymon_en

* Add model 2024-08-20-mt5_base_zhquad_qg_pipeline_zh

* Add model 2024-08-20-t5_base_samsum_seed42_en

* Add model 2024-08-20-w5_tp_bhc_long_t5_local_base_en

* Add model 2024-08-20-w5_tp_bhc_long_t5_local_base_pipeline_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_szymon_pipeline_en

* Add model 2024-08-20-t5_base_samsum_seed42_pipeline_en

* Add model 2024-08-20-flan_t5_large_danish_multiwoz2_1_fs0_01_en

* Add model 2024-08-20-flan_t5_large_danish_multiwoz2_1_fs0_01_pipeline_en

* Add model 2024-08-20-t5large_hate_speech_adv_md5_0_en

* Add model 2024-08-20-t5large_hate_speech_adv_md5_0_pipeline_en

* Add model 2024-08-20-english_vietnamese_mt5_base_news_train_en

* Add model 2024-08-20-english_vietnamese_mt5_base_news_train_pipeline_en

* Add model 2024-08-20-burmese_t5_strange_answering_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_spanish_illuminarchie_en

* Add model 2024-08-20-t5_base_detox_en

* Add model 2024-08-20-burmese_t5_strange_answering_pipeline_en

* Add model 2024-08-20-t5_base_detox_pipeline_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_english_spanish_illuminarchie_pipeline_en

* Add model 2024-08-20-dutch_ge_25_6b_3ep_northern_sami_en

* Add model 2024-08-20-bangla_para_v3_210000_en

* Add model 2024-08-20-bangla_para_v3_210000_pipeline_en

* Add model 2024-08-20-dutch_ge_25_6b_3ep_northern_sami_pipeline_en

* Add model 2024-08-20-translation_spanish_en

* Add model 2024-08-20-translation_spanish_pipeline_en

* Add model 2024-08-20-t5_large_mod_translation_en

* Add model 2024-08-20-t5_large_mod_translation_pipeline_en

* Add model 2024-08-20-mt5_base_bangla_para_v1_en

* Add model 2024-08-20-mt5_base_bangla_para_v1_pipeline_en

* Add model 2024-08-20-ft_aeroqa_1hop_aviationcorpusandaviationtriples_20_en

* Add model 2024-08-20-cs505_coqe_vit5_total_instruction4_opasl_v1_en

* Add model 2024-08-20-ft_aeroqa_1hop_aviationcorpusandaviationtriples_20_pipeline_en

* Add model 2024-08-20-question_answer_model_en

* Add model 2024-08-20-question_answer_model_pipeline_en

* Add model 2024-08-20-cs341_camera_coqe_unicoqe_t5small_en

* Add model 2024-08-20-cs341_camera_coqe_unicoqe_t5small_pipeline_en

* Add model 2024-08-20-flan_t5_small_comma_correction_en

* Add model 2024-08-20-flan_t5_small_comma_correction_pipeline_en

* Add model 2024-08-20-ft_aeroqa_1hop_aviationtriples_unverb_20_en

* Add model 2024-08-20-ft_aeroqa_1hop_aviationtriples_unverb_20_pipeline_en

* Add model 2024-08-20-burmese_samsum_model_en

* Add model 2024-08-20-burmese_samsum_model_pipeline_en

* Add model 2024-08-20-kltn_coqe_vit5_total_spaol_v5_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_chinese_en

* Add model 2024-08-20-mt5_small_finetuned_amazon_chinese_pipeline_en

* Add model 2024-08-20-text_exps_t5_20_aug_pipeline_en

* Add model 2024-08-20-kltn_coqe_vit5_total_spaol_v5_pipeline_en

* Add model 2024-08-20-text_exps_t5_20_aug_en

* Add model 2024-08-20-wikit5_en

* Add model 2024-08-20-wikit5_pipeline_en

* Add model 2024-08-20-pretrain_law_model_vit5_version3_en

* Add model 2024-08-20-t5model100_en

* Add model 2024-08-20-t5model100_pipeline_en

* Add model 2024-08-20-pretrain_law_model_vit5_version3_pipeline_en

* Add model 2024-08-20-mt5_small_czech_10k_en

* Add model 2024-08-20-mt5_small_czech_10k_pipeline_en

* Add model 2024-08-20-flan_t5_large_fold_2_en

* Add model 2024-08-20-cs505_coqe_vit5_train_instruction4_paosl_v1_en

* Add model 2024-08-20-wikihow_t5_small_finetuned_pubmed_en

* Add model 2024-08-20-wikihow_t5_small_finetuned_pubmed_pipeline_en

* Add model 2024-08-20-cs505_coqe_vit5_train_instruction4_paosl_v1_pipeline_en

* Add model 2024-08-20-cs505_coqe_vit5_train_instructionn0_ospal_v1_en

* Add model 2024-08-20-cs505_coqe_vit5_train_instructionn0_ospal_v1_pipeline_en

* Add model 2024-08-20-t5_base_sft_books_en

* Add model 2024-08-20-t5_base_sft_books_pipeline_en

* Add model 2024-08-20-mt5_baseline_en

* Add model 2024-08-20-mt5_small_trimmed_italian_10000_itquad_qg_it

* Add model 2024-08-20-mt5_small_trimmed_italian_10000_itquad_qg_pipeline_it

* Add model 2024-08-20-mt5_baseline_pipeline_en

* Add model 2024-08-20-norwegian_sum_t5_6_en

* Add model 2024-08-20-frame_semantic_transformer_google_t5_efficient_tiny_en

* Add model 2024-08-20-norwegian_sum_t5_6_pipeline_en

* Add model 2024-08-20-frame_semantic_transformer_google_t5_efficient_tiny_pipeline_en

* Add model 2024-08-20-mt5_base_finetuned_kazakh_tonga_tonga_islands_english_dump_people_en

* Add model 2024-08-20-vit5_viquad_en

* Add model 2024-08-20-vit5_viquad_pipeline_en

* Add model 2024-08-20-t5large_hate_speech_syntactic_adv_instruction_2_en

* Add model 2024-08-20-t5large_hate_speech_syntactic_adv_instruction_2_pipeline_en

* Add model 2024-08-20-cs505_coqe_vit5_train_instruction0_osapl_en

* Add model 2024-08-20-t5_4m_en

* Add model 2024-08-20-flanwithoutpassage_en

* Add model 2024-08-20-cs505_coqe_vit5_train_instruction0_osapl_pipeline_en

* Add model 2024-08-20-mt5_small_all_25000_en

* Add model 2024-08-20-flanwithoutpassage_pipeline_en

* Add model 2024-08-20-mt5_small_all_25000_pipeline_en

* Add model 2024-08-20-t5_4m_pipeline_en

* Add model 2024-08-20-deed_summarization_mt5_version_1_en

* Add model 2024-08-20-deed_summarization_mt5_version_1_pipeline_en

* Add model 2024-08-20-test_k2t_en

* Add model 2024-08-20-test_k2t_pipeline_en

* Add model 2024-08-20-boolq_t5_base_seed_1_en

* Add model 2024-08-20-boolq_t5_base_seed_1_pipeline_en

* Add model 2024-08-20-cs505_coqe_vit5_total_instruction0_saopl_v1_en

* Add model 2024-08-20-cs505_coqe_vit5_total_instruction0_saopl_v1_pipeline_en

* Add model 2024-08-20-t5large_hate_speech_syntactic_adv_instruction_0_en

* Add model 2024-08-20-burmese_awesome_modelv3_en

* Add model 2024-08-20-burmese_awesome_modelv3_pipeline_en

* Add model 2024-08-20-mt5_base_jaquad_qag_trimmed_50000_en

* Add model 2024-08-20-t5large_hate_speech_syntactic_adv_instruction_0_pipeline_en

* Add model 2024-08-20-mt5_base_jaquad_qag_trimmed_50000_pipeline_en

* Add model 2024-08-20-random_in_domain_5_demos_t5_small_en

* Add model 2024-08-20-random_in_domain_5_demos_t5_small_pipeline_en

* Add model 2024-08-20-t5_qg_model_with_answer2_en

* Add model 2024-08-20-grammer_en

* Add model 2024-08-20-t5_qg_model_with_answer2_pipeline_en

* Add model 2024-08-20-grammer_pipeline_en

* Add model 2024-08-20-legal_t5_small_trans_swedish_czech_small_finetuned_pipeline_en

* Add model 2024-08-20-text_sum_using_abstraction_en

* Add model 2024-08-20-t5_60m_lm_wmt_2012_2_en

* Add model 2024-08-20-t5_60m_lm_wmt_2012_2_pipeline_en

---------

Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>
  • Loading branch information
@jsl-models @ahmedlone127
jsl-models and ahmedlone127 authored Aug 20, 2024
1 parent ffb3b2a commit 04ebc29
Show file tree
Hide file tree
Showing 2,443 changed files with 189,784 additions and 0 deletions.
86 changes: 86 additions & 0 deletions docs/_posts/ahmedlone127/2024-08-17-albaniani_sum_v1_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,86 @@
---
layout: model
title: English albaniani_sum_v1 T5Transformer from mHossain
author: John Snow Labs
name: albaniani_sum_v1
date: 2024-08-17
tags: [en, open_source, onnx, t5, question_answering, summarization, translation, text_generation]
task: [Question Answering, Summarization, Translation, Text Generation]
language: en
edition: Spark NLP 5.4.2
spark_version: 3.0
supported: true
engine: onnx
annotator: T5Transformer
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained T5Transformer model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`albaniani_sum_v1` is a English model originally trained by mHossain.

{:.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/albaniani_sum_v1_en_5.4.2_3.0_1723915533205.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/albaniani_sum_v1_en_5.4.2_3.0_1723915533205.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')

t5 = T5Transformer.pretrained("albaniani_sum_v1","en") \
.setInputCols(["document"]) \
.setOutputCol("output")

pipeline = Pipeline().setStages([documentAssembler, t5])
data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)

```
```scala

val documentAssembler = new DocumentAssembler()
.setInputCols("text")
.setOutputCols("document")

val t5 = T5Transformer.pretrained("albaniani_sum_v1", "en")
.setInputCols(Array("documents"))
.setOutputCol("output")

val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))
val data = Seq("I love spark-nlp").toDS.toDF("text")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|albaniani_sum_v1|
|Compatibility:|Spark NLP 5.4.2+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[document]|
|Output Labels:|[output]|
|Language:|en|
|Size:|947.2 MB|

## References

https://huggingface.co/mHossain/Albaniani_sum_v1
69 changes: 69 additions & 0 deletions docs/_posts/ahmedlone127/2024-08-17-albaniani_sum_v1_pipeline_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
---
layout: model
title: English albaniani_sum_v1_pipeline pipeline T5Transformer from mHossain
author: John Snow Labs
name: albaniani_sum_v1_pipeline
date: 2024-08-17
tags: [en, open_source, pipeline, onnx]
task: [Question Answering, Summarization, Translation, Text Generation]
language: en
edition: Spark NLP 5.4.2
spark_version: 3.0
supported: true
annotator: PipelineModel
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`albaniani_sum_v1_pipeline` is a English model originally trained by mHossain.

{:.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/albaniani_sum_v1_pipeline_en_5.4.2_3.0_1723915596902.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/albaniani_sum_v1_pipeline_en_5.4.2_3.0_1723915596902.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

pipeline = PretrainedPipeline("albaniani_sum_v1_pipeline", lang = "en")
annotations = pipeline.transform(df)

```
```scala

val pipeline = new PretrainedPipeline("albaniani_sum_v1_pipeline", lang = "en")
val annotations = pipeline.transform(df)

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|albaniani_sum_v1_pipeline|
|Type:|pipeline|
|Compatibility:|Spark NLP 5.4.2+|
|License:|Open Source|
|Edition:|Official|
|Language:|en|
|Size:|947.2 MB|

## References

https://huggingface.co/mHossain/Albaniani_sum_v1

## Included Models

- DocumentAssembler
- T5Transformer
86 changes: 86 additions & 0 deletions ...sts/ahmedlone127/2024-08-17-all_mt5_base_10_spider_15_wikisql_nepal_bhasa_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,86 @@
---
layout: model
title: English all_mt5_base_10_spider_15_wikisql_nepal_bhasa T5Transformer from e22vvb
author: John Snow Labs
name: all_mt5_base_10_spider_15_wikisql_nepal_bhasa
date: 2024-08-17
tags: [en, open_source, onnx, t5, question_answering, summarization, translation, text_generation]
task: [Question Answering, Summarization, Translation, Text Generation]
language: en
edition: Spark NLP 5.4.2
spark_version: 3.0
supported: true
engine: onnx
annotator: T5Transformer
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained T5Transformer model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`all_mt5_base_10_spider_15_wikisql_nepal_bhasa` is a English model originally trained by e22vvb.

{:.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/all_mt5_base_10_spider_15_wikisql_nepal_bhasa_en_5.4.2_3.0_1723939059076.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/all_mt5_base_10_spider_15_wikisql_nepal_bhasa_en_5.4.2_3.0_1723939059076.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')

t5 = T5Transformer.pretrained("all_mt5_base_10_spider_15_wikisql_nepal_bhasa","en") \
.setInputCols(["document"]) \
.setOutputCol("output")

pipeline = Pipeline().setStages([documentAssembler, t5])
data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)

```
```scala

val documentAssembler = new DocumentAssembler()
.setInputCols("text")
.setOutputCols("document")

val t5 = T5Transformer.pretrained("all_mt5_base_10_spider_15_wikisql_nepal_bhasa", "en")
.setInputCols(Array("documents"))
.setOutputCol("output")

val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))
val data = Seq("I love spark-nlp").toDS.toDF("text")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|all_mt5_base_10_spider_15_wikisql_nepal_bhasa|
|Compatibility:|Spark NLP 5.4.2+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[document]|
|Output Labels:|[output]|
|Language:|en|
|Size:|2.4 GB|

## References

https://huggingface.co/e22vvb/ALL_mt5-base_10_spider_15_wikiSQL_new
86 changes: 86 additions & 0 deletions docs/_posts/ahmedlone127/2024-08-17-attributes_latest_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,86 @@
---
layout: model
title: English attributes_latest T5Transformer from bitadin
author: John Snow Labs
name: attributes_latest
date: 2024-08-17
tags: [en, open_source, onnx, t5, question_answering, summarization, translation, text_generation]
task: [Question Answering, Summarization, Translation, Text Generation]
language: en
edition: Spark NLP 5.4.2
spark_version: 3.0
supported: true
engine: onnx
annotator: T5Transformer
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained T5Transformer model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`attributes_latest` is a English model originally trained by bitadin.

{:.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/attributes_latest_en_5.4.2_3.0_1723938821896.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/attributes_latest_en_5.4.2_3.0_1723938821896.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')

t5 = T5Transformer.pretrained("attributes_latest","en") \
.setInputCols(["document"]) \
.setOutputCol("output")

pipeline = Pipeline().setStages([documentAssembler, t5])
data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)

```
```scala

val documentAssembler = new DocumentAssembler()
.setInputCols("text")
.setOutputCols("document")

val t5 = T5Transformer.pretrained("attributes_latest", "en")
.setInputCols(Array("documents"))
.setOutputCol("output")

val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))
val data = Seq("I love spark-nlp").toDS.toDF("text")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|attributes_latest|
|Compatibility:|Spark NLP 5.4.2+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[document]|
|Output Labels:|[output]|
|Language:|en|
|Size:|1.0 GB|

## References

https://huggingface.co/bitadin/attributes-latest
Loading

0 comments on commit 04ebc29

Please sign in to comment.