2024-08-30-camembert_base_qa_fquad_fr (#14386)

* Add model 2024-09-01-m0_flat_ner_ocr_ptrn_cmbert_io_pipeline_fr

* Add model 2024-09-01-nermembert_base_3entities_fr

* Add model 2024-09-01-clip_vit_l_14_datacomp_xl_s13b_b90k_laion_en

* Add model 2024-09-01-roberta_base_ag_news_dasoteloro_pipeline_en

* Add model 2024-09-01-mongolian_distilbert_base_multilingual_cased_ner_pipeline_xx

* Add model 2024-09-01-burmese_awesome_wnut_model_nastyakorneeva_en

* Add model 2024-09-01-ner_tune_v2_42_en

* Add model 2024-09-01-robbert_2022_dutch_base_nl

* Add model 2024-09-01-xlmroberta_ner_k3nneth_base_finetuned_panx_pipeline_de

* Add model 2024-09-01-xlmroberta_ner_coolzhao_base_finetuned_panx_pipeline_de

* Add model 2024-09-01-ukrainian_punctcase_uk

* Add model 2024-09-01-xlmroberta_ner_k3nneth_base_finetuned_panx_de

* Add model 2024-09-01-xlm_roberta_base_finetuned_panx_german_french_iis2009002_pipeline_en

* Add model 2024-09-01-xlmroberta_ner_imyday_base_finetuned_panx_de

* Add model 2024-09-01-xlmroberta_ner_imyday_base_finetuned_panx_pipeline_de

* Add model 2024-09-01-serengeti_xx

* Add model 2024-09-01-fs_distilroberta_fine_tuned_pipeline_en

* Add model 2024-09-01-serengeti_pipeline_xx

* Add model 2024-09-01-robbert_2022_dutch_base_pipeline_nl

* Add model 2024-09-01-xlmroberta_ner_base_uncased_bc5cdr_pipeline_en

* Add model 2024-09-01-xlmroberta_ner_base_uncased_bc5cdr_en

* Add model 2024-09-01-xlm_roberta_base_panx_dataset_english_pipeline_en

* Add model 2024-09-01-nermembert_base_3entities_pipeline_fr

* Add model 2024-09-01-xlmroberta_ner_base_uncased_panx_dataset_en

* Add model 2024-09-01-xlmroberta_ner_ericklerouge123_base_finetuned_panx_de

* Add model 2024-09-01-qa_synthetic_data_only_21_aug_xlm_roberta_base_pipeline_en

* Add model 2024-09-01-burmese_awesome_wnut_model_nilesh05_en

* Add model 2024-09-01-xlmroberta_ner_zpablo_base_finetuned_panx_de

* Add model 2024-09-01-camembert_loc_pipeline_en

* Add model 2024-09-01-burmese_ner_model_amrita06_en

* Add model 2024-09-01-cpegen_vp_en

* Add model 2024-09-01-bert_general_disease_en

* Add model 2024-09-01-xlmroberta_ner_shopee_id

* Add model 2024-09-01-clip_zero_shot_image_classification_pipeline_en

* Add model 2024-09-01-xlmroberta_ner_xlm_roberta_base_finetuned_swahili_finetuned_ner_igbo_pipeline_ig

* Add model 2024-09-01-distilbert_base_uncased_finetuned_ner_meneiaus_pipeline_en

* Add model 2024-09-01-xlm_roberta_base_panx_dataset_arabic_en

* Add model 2024-09-01-xlm_roberta_base_panx_dataset_arabic_pipeline_en

* Add model 2024-09-01-20230327_baseline_xlmr_clickbait_spoiling_en

* Add model 2024-09-01-laberta_la

* Add model 2024-09-01-xlmroberta_ner_tner_base_uncased_ontonotes5_en

* Add model 2024-09-01-ae_detection_tac_data_pipeline_en

* Add model 2024-09-01-xlmroberta_ner_tner_base_uncased_ontonotes5_pipeline_en

* Add model 2024-09-01-code_segmentor_distilbert_en

* Add model 2024-09-01-xlmroberta_ner_haesun_base_finetuned_panx_all_pipeline_xx

* Add model 2024-09-01-legal_roberta_base_saibo_creator_pipeline_en

* Add model 2024-09-01-finetuned_distilbert_base_uncased_conll2003_test_after_optuna_hp_search_pipeline_en

* Add model 2024-09-01-burmese_awesome_wnut_model_agdsga_pipeline_en

* Add model 2024-09-01-finetuning_profane_model_deberta_en

* Add model 2024-09-01-xlmroberta_ner_base_uncased_panx_dataset_pipeline_en

* Add model 2024-09-01-finetuning_profane_model_deberta_pipeline_en

* Add model 2024-09-01-deberta_v3_base_nli_mixer_binary_pipeline_en

* Add model 2024-09-01-deberta_v3_large_finetuned_synthetic_multi_class_en

* Add model 2024-09-01-deberta_v3_amazon_reviews_pipeline_en

* Add model 2024-09-01-deberta_v3_large_finetuned_synthetic_multi_class_pipeline_en

* Add model 2024-09-01-deberta_v3_base_finetuned_sst2_en

* Add model 2024-09-01-deberta_v3_small_goemotions_en

* Add model 2024-09-01-deberta_v3_large__sst2__train_16_8_pipeline_en

* Add model 2024-09-01-clinicalbert_cancer_type_extraction_3_pipeline_en

* Add model 2024-09-01-deberta_v2_base_japanese_finetuned_wrime_pipeline_en

* Add model 2024-09-01-xlmroberta_ner_coolzhao_base_finetuned_panx_de

* Add model 2024-09-01-microsoft_deberta_v3_large_cls_subj_gladiator_pipeline_en

* Add model 2024-09-01-deberta_v2_base_japanese_finetuned_wrime_en

* Add model 2024-09-01-deberta_v3_small_finetuned_cola_mrm8488_pipeline_en

* Add model 2024-09-01-xlmroberta_ner_cole_base_finetuned_panx_pipeline_de

* Add model 2024-09-01-xlmroberta_ner_cole_base_finetuned_panx_de

* Add model 2024-09-01-mdebertav3_subjectivity_english_en

* Add model 2024-09-01-xlmroberta_ner_xlm_roberta_base_finetuned_yoruba_finetuned_ner_yoruba_pipeline_yo

* Add model 2024-09-01-xlm_roberta_base_language_detection_brenomatos_pipeline_en

* Add model 2024-09-01-mdebertav3_subjectivity_multilingual_pipeline_xx

* Add model 2024-09-01-distilbert_base_uncased_finetuned_ner_christiancad_en

* Add model 2024-09-01-burmese_awesome_distilbert_model_pipeline_en

* Add model 2024-09-01-deberta_v3_base_10xp3nirstbbflanse_5xc4_pipeline_en

* Add model 2024-09-01-burmese_awesome_wnut_them_pipeline_en

* Add model 2024-09-01-command_ner_distilbert_en

* Add model 2024-09-01-camembert_loc_en

* Add model 2024-09-01-deberta_v3_amazon_reviews_en

* Add model 2024-09-01-mdeberta_vitaminc_mnli_anli_wanli_lingnli_en

* Add model 2024-09-01-mdeberta_v3_base_vsfc_100_pipeline_en

* Add model 2024-09-01-clip_seed_vit_11_pipeline_en

* Add model 2024-09-01-hasoc19_microsoft_mdeberta_v3_base_targinsult1_pipeline_en

* Add model 2024-09-01-distilbert_infoextract_v2_en

* Add model 2024-09-01-bert_cas_model_beta_en

* Add model 2024-09-01-deberta_v3_large__sst2__train_16_5_en

* Add model 2024-09-01-microsoft_deberta_v3_large_cls_subj_gladiator_en

* Add model 2024-09-01-deberta_v3_small_finetuned_cola_mrm8488_en

* Add model 2024-09-01-roberta_large_emolit_pipeline_en

* Add model 2024-09-01-xlmroberta_ner_zpablo_base_finetuned_panx_pipeline_de

* Add model 2024-09-01-xlmroberta_ner_xlm_roberta_base_finetuned_hausa_finetuned_ner_hausa_pipeline_ha

* Add model 2024-09-01-burmese_awesome_conll_model_kheyh_en

* Add model 2024-09-01-deberta_v3_base_cotat_pipeline_en

* Add model 2024-09-01-infoxlm_base_pipeline_en

* Add model 2024-09-01-deberta_v3_large_survey_nepal_bhasa_fact_related_passage_rater_all_pipeline_en

* Add model 2024-09-01-deberta_v3_large__sst2__train_32_0_pipeline_en

* Add model 2024-09-01-bert_base_cased_cefr_abdulsami_en

* Add model 2024-09-01-deberta_v3_large_survey_main_passage_consistency_rater_en

* Add model 2024-09-01-deberta_v3_large_survey_main_passage_consistency_rater_pipeline_en

* Add model 2024-09-01-umberto_wikipedia_uncased_v1_finetuned_squadv1_italian_it

* Add model 2024-09-01-burmese_awesome_wnut_model_joddiy_pipeline_en

* Add model 2024-09-01-xlm_roberta_base_finetuned_on_runaways_dutch_pipeline_en

* Add model 2024-09-01-distilbert_base_uncased_finetuned_ner_itspxsh_pipeline_en

* Add model 2024-09-01-indobert_lite_squadx_pipeline_id

* Add model 2024-09-01-deberta_v3_base_10xp3_10xc4_512_en

* Add model 2024-09-01-xlmroberta_ner_yaxin_base_conll2003_en

* Add model 2024-09-01-answer_finder_yuzu_ja

* Add model 2024-09-01-answer_finder_yuzu_pipeline_ja

* Add model 2024-09-01-mobilebert_uncased_finetuned_squadv2_pipeline_en

* Add model 2024-09-01-mobilebert_uncased_finetuned_squadv2_en

* Add model 2024-09-01-bert_qa_youngjae_bert_finetuned_squad_en

* Add model 2024-09-01-mobilebert_uncased_squad_v2_csarron_pipeline_en

* Add model 2024-09-01-bert_qa_youngjae_bert_finetuned_squad_pipeline_en

* Add model 2024-09-01-twitter_xlm_roberta_base_pipeline_en

* Add model 2024-09-01-marathi_question_answering_squad_bert_pipeline_mr

* Add model 2024-09-01-rubert_large_squad_2_en

* Add model 2024-09-01-bert_large_uncased_whole_word_masking_finetuned_squad_google_bert_en

* Add model 2024-09-01-deberta_v3_large_survey_nepal_bhasa_fact_related_passage_rater_all_en

* Add model 2024-09-01-mdeberta_base_formality_ranker_en

* Add model 2024-09-01-distilbert_finetuned_ner_for_articles_pipeline_en

* Add model 2024-09-01-electra_qa_DSPFirst_Finetuning_5_pipeline_en

* Add model 2024-09-01-bert_large_uncased_whole_word_masking_finetuned_squad_google_bert_pipeline_en

* Add model 2024-09-01-clinicalbert_craft_ner_pipeline_en

* Add model 2024-09-01-ner_on_proteindata_pipeline_en

* Add model 2024-09-01-deberta_v3_base_10xp3nirstbbflanse_5xc4_en

* Add model 2024-09-01-model_2_en

* Add model 2024-09-01-serbian_roberta_base_pipeline_sr

* Add model 2024-09-01-roberta_large_unli_pipeline_en

* Add model 2024-09-01-legal_xlm_roberta_base_xx

* Add model 2024-09-01-burmese_awesome_wnut_model_sujit27_pipeline_en

* Add model 2024-09-01-burmese_awesome_wnut_model100_en

* Add model 2024-09-01-deberta_v3_dnli_pipeline_en

* Add model 2024-09-01-roberta_base_latin_cased_pipeline_en

* Add model 2024-09-01-roberta_base_latin_cased_en

* Add model 2024-09-01-kcbert_v2023_pipeline_en

* Add model 2024-09-01-greeklegalroberta_v3_pipeline_el

* Add model 2024-09-01-greeklegalroberta_v3_el

* Add model 2024-09-01-roberta_urdu_small_ur

* Add model 2024-09-01-roberta_urdu_small_pipeline_ur

* Add model 2024-09-01-deberta_v3_large_survey_cross_passage_consistency_rater_gpt4_en

* Add model 2024-09-01-deberta_v3_large__sst2__train_8_2_pipeline_en

* Add model 2024-09-01-hero_he

* Add model 2024-09-01-hero_pipeline_he

* Add model 2024-09-01-xlm_roberta_base_finetuned_panx_german_munsu_pipeline_en

* Add model 2024-09-01-bpe_selfies_pubchem_shard00_160k_en

* Add model 2024-09-01-electra_qa_DSPFirst_Finetuning_5_en

* Add model 2024-09-01-twitter_roberta_base_2021_124m_en

* Add model 2024-09-01-wangchanberta_thai_wiki_qa_hyp_params_pipeline_th

* Add model 2024-09-01-deberta_v3_base_10xp3_10xc4_512_pipeline_en

* Add model 2024-09-01-burmese_awesome_wnut_model_risho_pipeline_en

* Add model 2024-09-01-distilbert_infoextract_v3_en

* Add model 2024-09-01-npm_single_pipeline_en

* Add model 2024-09-01-finetuned_camembert_for_job_offers_en

* Add model 2024-09-01-legal_xlm_roberta_base_pipeline_xx

* Add model 2024-09-01-bilingualchildemo_pipeline_en

* Add model 2024-09-01-marathisentiment_mr

* Add model 2024-09-01-sentiment_en

* Add model 2024-09-01-sentiment_pipeline_en

* Add model 2024-09-01-codebert_javascript_pipeline_en

* Add model 2024-09-01-ogbv_gender_indicbert_tamil_eacl_finals_en

* Add model 2024-09-01-ogbv_gender_indicbert_tamil_eacl_finals_pipeline_en

* Add model 2024-09-01-scandibert_ner_pipeline_en

* Add model 2024-09-01-burmese_model_pipeline_en

* Add model 2024-09-01-model_2_pipeline_en

* Add model 2024-09-01-dr_bertfinetuned_huge_19_bios_large_en

* Add model 2024-09-01-deberta_v3_large__sst2__train_32_0_en

* Add model 2024-09-01-roberta_sentiment_persian_pipeline_fa

* Add model 2024-09-01-twitter_xlm_roberta_base_en

* Add model 2024-09-01-distilbert_ner_saugatkafley_pipeline_en

* Add model 2024-09-01-kpf_bert_ner_kpf_pipeline_en

* Add model 2024-09-01-test_sup_only_ct_qa_002_13june23_1_en

* Add model 2024-09-01-xlm_roberta_base_fire_classification_silvanus_pipeline_xx

* Add model 2024-09-01-trained_polish_pipeline_en

* Add model 2024-09-01-outputs_bittar_pipeline_en

* Add model 2024-09-01-xlm_roberta_base_toxicity_pipeline_es

* Add model 2024-09-01-crossencoder_mminilmv2_l12_mmarcofr_fr

* Add model 2024-09-01-bert_qa_bert_mini_finetuned_squadv2_pipeline_en

* Add model 2024-09-01-burmese_awesome_wnut_model_joddiy_en

* Add model 2024-09-01-bert_qa_bert_mini_finetuned_squadv2_en

* Add model 2024-09-01-mdeberta_v3_base_vsfc_100_en

* Add model 2024-09-01-token_classifier_en

* Add model 2024-09-01-marathisentiment_pipeline_mr

* Add model 2024-09-01-sentiment_hts5_xlm_roberta_hungarian_hu

* Add model 2024-09-01-m3_hierarchical_ner_ocr_ptrn_cmbert_io_pipeline_fr

* Add model 2024-09-01-english_multinerd_masked_ner_more_training_en

* Add model 2024-09-01-mminilmv2_l6_h384_distilled_from_xlmr_large_enod_en

* Add model 2024-09-01-korean_finance_news_classifier_pipeline_en

* Add model 2024-09-01-indic_bert_finetuned_ours_ds_pipeline_en

* Add model 2024-09-01-xlm_roberta_hate_final_en

* Add model 2024-09-01-mminilm_l6_v2_english_msmarco_en

* Add model 2024-09-01-xlm_roberta_base_finetuned_marc_english_krassy_pipeline_en

* Add model 2024-09-01-xlm_roberta_hate_final_pipeline_en

* Add model 2024-09-01-xlmroberta_ner_xlm_roberta_base_finetuned_yoruba_finetuned_ner_yoruba_yo

* Add model 2024-09-01-social_movement_stance_en

* Add model 2024-09-01-bert_ner_idrisi_lmr_hd_tagalog_en

* Add model 2024-09-01-bpe_selfies_pubchem_shard00_160k_pipeline_en

* Add model 2024-09-01-crossencoder_me5_base_mmarcofr_pipeline_fr

* Add model 2024-09-01-xlm_roberta_base_finetuned_italian_english_classification_ticket_en

* Add model 2024-09-01-xlm_roberta_base_finetuned_italian_english_classification_ticket_pipeline_en

* Add model 2024-09-01-xlm_roberta_base_language_detection_silvanus_pipeline_xx

* Add model 2024-09-01-roberta_nsfw_text_classifier_pipeline_en

* Add model 2024-09-01-fewshot_qa_002_20230613_003_en

* Add model 2024-09-01-deberta_v3_large_finetuned_syndag_multiclass_not_bloom_en

* Add model 2024-09-01-ethicaleye_xx

* Add model 2024-09-01-deberta_v3_base_optimus_v0_pipeline_en

* Add model 2024-09-01-ner_classification_en

* Add model 2024-09-01-kcbert_v2023_en

* Add model 2024-09-01-model_api_test_pipeline_en

* Add model 2024-09-01-xlm_roberta_base_finetuned_marc_english_pratibha_pipeline_en

* Add model 2024-09-01-emubert_en

* Add model 2024-09-01-korean_finance_news_classifier_en

* Add model 2024-09-01-bantuberta_xx

* Add model 2024-09-01-roberta_base_wechsel_swahili_sw

* Add model 2024-09-01-distilroberta_base_climate_s_en

* Add model 2024-09-01-ct_m2_bestloss_pipeline_en

* Add model 2024-09-01-twitter_roberta_base_sep2022_pipeline_en

* Add model 2024-09-01-danskbert_pipeline_da

* Add model 2024-09-01-socialbert_base_en

* Add model 2024-09-01-roberta_base_model_attribution_challenge_en

* Add model 2024-09-01-mi_roberta_base_v2_en

* Add model 2024-09-01-mi_roberta_base_v2_pipeline_en

* Add model 2024-09-01-roberta_base_biomedical_clinical_spanish_bsc_lt_pipeline_es

* Add model 2024-09-01-robbert_base_en

* Add model 2024-09-01-sentareng_v0_pipeline_en

* Add model 2024-09-01-secureshellbert_pipeline_en

* Add model 2024-09-01-deberta_v3_large__sst2__train_16_8_en

* Add model 2024-09-01-edos_2023_baseline_xlm_roberta_base_label_vector_en

* Add model 2024-09-01-mminilmv2_l6_h384_distilled_from_xlmr_large_enod_pipeline_en

* Add model 2024-09-01-distilbert_base_multilingual_cased_ner_demo_pipeline_xx

* Add model 2024-09-01-distilbert_base_multilingual_cased_ner_demo_xx

* Add model 2024-09-01-edos_2023_baseline_xlm_roberta_base_label_vector_pipeline_en

* Add model 2024-09-01-burmese_awesome_wnut_model_kolegas_en

* Add model 2024-09-01-burmese_awesome_wnut_them_all_en

* Add model 2024-09-01-pretrained_xlm_portuguese_e8_all_pipeline_en

* Add model 2024-09-01-bce_reranker_base_v1_infiniflow_en

* Add model 2024-09-01-xlmroberta_ner_jgriffi_base_finetuned_panx_en

* Add model 2024-09-01-burmese_qa_model_en

* Add model 2024-09-01-bce_reranker_base_v1_infiniflow_pipeline_en

* Add model 2024-09-01-malayalambert_pipeline_en

* Add model 2024-09-01-distilbert_base_uncased_finetuned_ner_kamaljp_pipeline_en

* Add model 2024-09-01-emubert_pipeline_en

* Add model 2024-09-01-albert_base_qa_3_en

* Add model 2024-09-01-albert_finetuned_chennaiqa_final_en

* Add model 2024-09-01-albert_finetuned_chennaiqa_final_pipeline_en

* Add model 2024-09-01-socialbert_base_pipeline_en

* Add model 2024-09-01-m2_joint_label_ocr_cmbert_io_pipeline_fr

* Add model 2024-09-01-crossencoder_me5_base_mmarcofr_fr

* Add model 2024-09-01-question_answering_albert_base_en

* Add model 2024-09-01-albert_base_finetuned_recipe_modified_pipeline_en

* Add model 2024-09-01-burmese_awesome_wnut_all_jaoo_en

* Add model 2024-09-01-distilbert_base_uncased_finetuned_srl_abritez_en

* Add model 2024-09-01-scamllm_en

---------

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

docs/_posts/ahmedlone127/2024-08-30-camembert_base_qa_fquad_fr.md

@@ -0,0 +1,113 @@
+---
+layout: model
+title: French CamemBertForQuestionAnswering Base squadFR (camembert_base_qa_fquad)
+author: John Snow Labs
+name: camembert_base_qa_fquad
+date: 2024-08-30
+tags: [fr, french, question_answering, camembert, open_source, onnx, openvino]
+task: Question Answering
+language: fr
+edition: Spark NLP 5.4.2
+spark_version: 3.0
+supported: true
+engine: openvino
+annotator: BertForZeroShotClassification
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained CamemBertForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `camembert_base_qa_fquad ` is a French model originally fine-tuned on a combo of three French Q&A datasets:
+
+- PIAFv1.1
+- FQuADv1.0
+- SQuAD-FR (SQuAD automatically translated to French)
+
+## 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/camembert_base_qa_fquad_fr_5.4.2_3.0_1725015714535.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/camembert_base_qa_fquad_fr_5.4.2_3.0_1725015714535.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 = MultiDocumentAssembler()\
+     .setInputCols(["question", "context"])\
+     .setOutputCols(["document_question", "document_context"])
+
+Question_Answering = CamemBertForQuestionAnswering("camembert_base_qa_fquad","fr")\
+     .setInputCols(["document_question", "document_context"])\
+     .setOutputCol("answer")\
+     .setCaseSensitive(True)
+
+pipeline = Pipeline(stages=[Document_Assembler, Question_Answering])
+
+data = spark.createDataFrame([["Où est-ce que je vis?","Mon nom est Wolfgang et je vis à Berlin."]]).toDF("question", "context")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val Document_Assembler = new MultiDocumentAssembler()
+     .setInputCols(Array("question", "context"))
+     .setOutputCols(Array("document_question", "document_context"))
+
+val Question_Answering = CamemBertForQuestionAnswering("camembert_base_qa_fquad","fr")
+     .setInputCols(Array("document_question", "document_context"))
+     .setOutputCol("answer")
+     .setCaseSensitive(True)
+
+val pipeline = new Pipeline().setStages(Array(Document_Assembler, Question_Answering))
+
+val data = Seq("Où est-ce que je vis?","Mon nom est Wolfgang et je vis à Berlin.").toDS.toDF("question", "context")
+
+val result = pipeline.fit(data).transform(data)
+```
+
+{:.nlu-block}
+```python
+import nlu
+nlu.load("fr.answer_question.camembert.fquad").predict("""Où est-ce que je vis?|||"Mon nom est Wolfgang et je vis à Berlin.""")
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|camembert_base_qa_fquad|
+|Compatibility:|Spark NLP 5.4.2+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[token, document]|
+|Output Labels:|[label]|
+|Language:|fr|
+|Size:|667.9 MB|
+|Case sensitive:|true|
+
+## References
+
+References
+
+References
+
+https://huggingface.co/etalab-ia/camembert-base-squadFR-fquad-piaf
+
+## Benchmarking
+
+```bash
+
+
+{"f1": 80.61, "exact_match": 59.54}
+```

docs/_posts/ahmedlone127/2024-08-30-combined_flan_t5_xl_classifier_en.md

@@ -0,0 +1,86 @@
+---
+layout: model
+title: English combined_flan_t5_xl_classifier T5Transformer from illuminoplanet
+author: John Snow Labs
+name: combined_flan_t5_xl_classifier
+date: 2024-08-30
+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.`combined_flan_t5_xl_classifier` is a English model originally trained by illuminoplanet.
+
+{:.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/combined_flan_t5_xl_classifier_en_5.4.2_3.0_1725048919360.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/combined_flan_t5_xl_classifier_en_5.4.2_3.0_1725048919360.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("combined_flan_t5_xl_classifier","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("combined_flan_t5_xl_classifier", "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:|combined_flan_t5_xl_classifier|
+|Compatibility:|Spark NLP 5.4.2+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document]|
+|Output Labels:|[output]|
+|Language:|en|
+|Size:|2.9 GB|
+
+## References
+
+https://huggingface.co/illuminoplanet/combined_flan_t5_xl_classifier

docs/_posts/ahmedlone127/2024-08-30-combined_flan_t5_xl_classifier_pipeline_en.md

@@ -0,0 +1,69 @@
+---
+layout: model
+title: English combined_flan_t5_xl_classifier_pipeline pipeline T5Transformer from illuminoplanet
+author: John Snow Labs
+name: combined_flan_t5_xl_classifier_pipeline
+date: 2024-08-30
+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.`combined_flan_t5_xl_classifier_pipeline` is a English model originally trained by illuminoplanet.
+
+{:.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/combined_flan_t5_xl_classifier_pipeline_en_5.4.2_3.0_1725049073632.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/combined_flan_t5_xl_classifier_pipeline_en_5.4.2_3.0_1725049073632.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("combined_flan_t5_xl_classifier_pipeline", lang = "en")
+annotations =  pipeline.transform(df)   
+
+```
+```scala
+
+val pipeline = new PretrainedPipeline("combined_flan_t5_xl_classifier_pipeline", lang = "en")
+val annotations = pipeline.transform(df)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|combined_flan_t5_xl_classifier_pipeline|
+|Type:|pipeline|
+|Compatibility:|Spark NLP 5.4.2+|
+|License:|Open Source|
+|Edition:|Official|
+|Language:|en|
+|Size:|2.9 GB|
+
+## References
+
+https://huggingface.co/illuminoplanet/combined_flan_t5_xl_classifier
+
+## Included Models
+
+- DocumentAssembler
+- T5Transformer

docs/_posts/ahmedlone127/2024-08-30-mt5_tsonga_para_en.md

@@ -0,0 +1,86 @@
+---
+layout: model
+title: English mt5_tsonga_para T5Transformer from boneb
+author: John Snow Labs
+name: mt5_tsonga_para
+date: 2024-08-30
+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.`mt5_tsonga_para` is a English model originally trained by boneb.
+
+{:.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/mt5_tsonga_para_en_5.4.2_3.0_1725052109767.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mt5_tsonga_para_en_5.4.2_3.0_1725052109767.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("mt5_tsonga_para","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("mt5_tsonga_para", "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:|mt5_tsonga_para|
+|Compatibility:|Spark NLP 5.4.2+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document]|
+|Output Labels:|[output]|
+|Language:|en|
+|Size:|2.3 GB|
+
+## References
+
+https://huggingface.co/boneb/mt5-TS-para