Skip to content

Commit

Permalink
2024-09-16-finetuning_sentiment_model_3000_samples_sarathaer_en (#14407)
Browse files Browse the repository at this point in the history 
* Add model 2024-09-20-distilbert_base_uncased_odm_zphr_0st5sd_ut72ut1_plprefix0stlarge5_simsp100_en

* Add model 2024-09-21-finetuning_sentiment_model_3000_samples_diegodelvalle_en

* Add model 2024-09-23-burmese_awesome_eli5_mlm_model_waterboy111_en

* Add model 2024-09-20-xlm_roberta_base_finetuned_panx_english_andrew45_pipeline_en

* Add model 2024-09-20-bert_base_klue_mrc_finetuned_jihoonkimharu_pipeline_ko

* Add model 2024-09-21-roberta_news_cnn_dailymail_pipeline_en

* Add model 2024-09-18-emotions_classifier_en

* Add model 2024-09-16-xlm_roberta_base_finetuned_panx_all_jhagege_en

* Add model 2024-09-22-burmese_awesome_model2_cippppy_pipeline_en

* Add model 2024-09-23-sst5_padding20model_pipeline_en

* Add model 2024-09-16-whisper_v4_small_en

* Add model 2024-09-23-sent_bert_base_uncased_issues_128_bh8648_en

* Add model 2024-09-21-whisper_small_oriya_v1_3_or

* Add model 2024-09-22-twitchleaguebert_260k_pipeline_en

* Add model 2024-09-23-sent_bert_large_cased_sigir_support_refute_norwegian_label_40_2nd_test_lr10_8_fast_4_en

* Add model 2024-09-23-sent_bert_base_uncased_danish_da

* Add model 2024-09-23-sent_bert_large_cased_sigir_support_refute_norwegian_label_40_2nd_test_lr10_8_fast_4_pipeline_en

* Add model 2024-09-16-roberta_base_squad_model1_pipeline_en

* Add model 2024-09-23-sent_bert_base_english_norwegian_cased_en

* Add model 2024-09-15-distilbert_base_uncased_finetuned_squad_manik114_pipeline_en

* Add model 2024-09-23-sent_bert_base_english_norwegian_cased_pipeline_en

* Add model 2024-09-23-sent_tiny_mlm_glue_mrpc_en

* Add model 2024-09-08-token_classification_test_sahithiankireddy_pipeline_en

* Add model 2024-09-19-roberta_base_finetuned_ring_en

* Add model 2024-09-16-whisper_medium_english_atco2_asr_en

* Add model 2024-09-23-sent_bert_persian_farsi_base_uncased_nlp_course_hw2_en

* Add model 2024-09-23-bge_large_repmus_cross_entropy_en

* Add model 2024-09-22-auro_1_pipeline_en

* Add model 2024-09-23-hate_hate_balance_random2_seed0_twitter_roberta_base_2021_124m_pipeline_en

* Add model 2024-09-20-tmp_trainer_vicman229_en

* Add model 2024-09-23-bert_base_uncased_finetuned_mrpc_w05230505_en

* Add model 2024-09-22-modelofine4_pipeline_en

* Add model 2024-09-22-roberta_base_plausibility_pipeline_en

* Add model 2024-09-20-finetuning_sentiment_model_3000_samples_naomaru_pipeline_en

* Add model 2024-09-23-whisper_small_danish_wasurats_pipeline_da

* Add model 2024-09-19-roberta_base_epoch_61_pipeline_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_clinc_fibleep_pipeline_en

* Add model 2024-09-17-lab1_finetuning_yimeiyang_pipeline_en

* Add model 2024-09-22-hate_hate_balance_random3_seed1_bertweet_large_en

* Add model 2024-09-19-whisper_big_kmon_pipeline_en

* Add model 2024-09-19-sentiment_multilingual_distilbert_pipeline_xx

* Add model 2024-09-18-distilbert_base_uncased_finetuned_emotion_sj1011_pipeline_en

* Add model 2024-09-21-bert_base_squad_v1_1_portuguese_ibama_v0_420240915010230_pipeline_en

* Add model 2024-09-21-distilbert_agnews_padding30model_en

* Add model 2024-09-23-legal_gqa_bert_augmented_1000_pipeline_en

* Add model 2024-09-23-xlmr_estonian_english_all_shuffled_2020_test1000_en

* Add model 2024-09-22-distilbert_base_uncased_cext_mypersonality_pipeline_en

* Add model 2024-09-10-roberta_base_roberta_model_enyonam_pipeline_en

* Add model 2024-09-14-whisper_small_fine_tuned_russian_pipeline_en

* Add model 2024-09-21-whisper_small_bengali_our_dataset_grapheme_en

* Add model 2024-09-23-xlm_roberta_base_text_classification_pipeline_en

* Add model 2024-09-23-base_12_pipeline_tr

* Add model 2024-09-23-distilroberta_rb156k_opt15_ep20_pipeline_en

* Add model 2024-09-22-sentiment1_en

* Add model 2024-09-21-saved_model_en

* Add model 2024-09-23-viz_wiz_bert_base_uncased_f16_pipeline_en

* Add model 2024-09-17-xlm_roberta_base_mongolian_ner_pipeline_mn

* Add model 2024-09-21-distilbert_base_uncased_finetuned_emotion_dasooo_pipeline_en

* Add model 2024-09-18-toxicdistilbert_en

* Add model 2024-09-19-distilbert_base_uncased_finetuned_bentleyjeon_pipeline_en

* Add model 2024-09-19-ct_m1_complete_pipeline_en

* Add model 2024-09-14-finetune4en_vietnamese_pipeline_en

* Add model 2024-09-18-ooc_patch_v1_pipeline_en

* Add model 2024-09-18-t_8_pipeline_en

* Add model 2024-09-18-distilbert_base_uncased_kitchen_and_dining_zphr_0st72_ut52ut1_plain_simsp_pipeline_en

* Add model 2024-09-09-roberta_base_corener_en

* Add model 2024-09-23-distilbert_base_uncased_finetuned_adl_hw1_alkhwarizmi_en

* Add model 2024-09-23-bert_large_uncased_whole_word_masking_finetuned_squad_dev_one_en

* Add model 2024-09-23-text_entity_recognigtion_en

* Add model 2024-09-23-text_entity_recognigtion_pipeline_en

* Add model 2024-09-23-distilbert_base_uncased_odm_zphr_0st19sd_ut72ut1_plprefix0stlarge_simsp300_pipeline_en

* Add model 2024-09-23-distilbert_base_uncased_travel_zphr_0st_ut72ut1_plainprefix_simsp_en

* Add model 2024-09-23-red_green_classification_v3_en

* Add model 2024-09-23-distilbert_base_uncased_odm_zphr_0st42sd_ut72ut1_plprefix0stlarge30_simsp_en

* Add model 2024-09-20-finetuning_sentiment_model_3004_samples_valliyammai_en

* Add model 2024-09-23-sent_bert_base_uncased_mnli_sparse_70_unstructured_norwegian_classifier_pipeline_en

* Add model 2024-09-14-xlm_roberta_base_finetuned_panx_all_wooseok0303_pipeline_en

* Add model 2024-09-19-distilbert_base_uncased_small_talk_zphr_2st_en

* Add model 2024-09-23-sent_defsent_bert_base_uncased_max_pipeline_en

* Add model 2024-09-23-sent_bert_base_uncased_issues_128_seddiktrk_en

* Add model 2024-09-23-distilbert_base_uncased_finetuned_emotion_ziwone_en

* Add model 2024-09-17-influence_tactic_paper_pipeline_en

* Add model 2024-09-23-bert_large_cased_scmedium_squad_pipeline_en

* Add model 2024-09-15-distilbertbaselinethreeepochevaluate_en

* Add model 2024-09-20-burmese_awesome_model_gamdalf_en

* Add model 2024-09-21-fine_tuned_distilbert_pipeline_en

* Add model 2024-09-20-roberta_agnews_padding20model_en

* Add model 2024-09-20-llmhw01_wsyar_en

* Add model 2024-09-19-distilbert_anandharaju_en

* Add model 2024-09-19-nepal_bhasa_bert_pipeline_en

* Add model 2024-09-23-sent_bert_ltrc_telugu_pipeline_en

* Add model 2024-09-23-sent_bert_ltrc_telugu_en

* Add model 2024-09-23-sent_bert_base_uncased_finetuned_wallisian_manual_2ep_lower_pipeline_en

* Add model 2024-09-23-sent_small_mlm_rotten_tomatoes_custom_tokenizer_en

* Add model 2024-09-23-sent_german_english_code_switching_bert_en

* Add model 2024-09-23-sent_bert_base_dutch_cased_finetuned_manx_pipeline_en

* Add model 2024-09-23-sent_german_english_code_switching_bert_pipeline_en

* Add model 2024-09-23-sent_bert_pretrained_wikitext_2_raw_v1_dimpo_pipeline_en

* Add model 2024-09-23-sent_hindi_bert_en

* Add model 2024-09-18-roberta_base_finetuned_1_pipeline_en

* Add model 2024-09-22-1121223_hw01_en

* Add model 2024-09-23-distilbert_base_uncased_finetuned_pad_clf_v2_en

* Add model 2024-09-23-test_model_peace5544_pipeline_en

* Add model 2024-09-23-test_model_peace5544_en

* Add model 2024-09-12-marefa_maltese_english_arabic_parallel_10k_splitted_euclidean_pipeline_en

* Add model 2024-09-23-distilbert_base_uncased_odm_zphr_0st16sd_ut72ut3_plprefix0stlarge_simsp100_clean100_en

* Add model 2024-09-23-burmese_awesome_model_omertnks_pipeline_en

* Add model 2024-09-23-n_distilbert_twitterfin_padding30model_pipeline_en

* Add model 2024-09-22-gs3n_roberta_model_es

* Add model 2024-09-23-nameattrsbert_pipeline_en

* Add model 2024-09-22-n_distilbert_imdb_padding90model_en

* Add model 2024-09-23-detect_femicide_news_xlmr_dutch_mono_freeze2_en

* Add model 2024-09-11-best_model_yelp_polarity_16_87_pipeline_en

* Add model 2024-09-20-xlm_roberta_base_finetuned_panx_german_vantaa32_en

* Add model 2024-09-23-hindi_bpe_bert_test_2m_en

* Add model 2024-09-20-finetuning_sentiment_model_3000_samples_3_pipeline_en

* Add model 2024-09-23-correct_bert_token_itr0_0_0001_all_01_03_2022_15_52_19_pipeline_en

* Add model 2024-09-22-bert_vllm_gemma2b_llmoversight_0_5_nodropsus_6_en

* Add model 2024-09-14-ner_roberta_en

* Add model 2024-09-15-roberta_base_finetuned_squad_ngchuchi_en

* Add model 2024-09-21-sent_arabertmo_base_v4_pipeline_ar

* Add model 2024-09-22-test_roberta_euhaq_pipeline_en

* Add model 2024-09-18-sent_bert_base_uncased_issues_128_martinwunderlich_en

* Add model 2024-09-22-strategytransitionplanv1_en

* Add model 2024-09-16-maltese_coref_english_spanish_gender_exp_en

* Add model 2024-09-23-bert_finetuned_ner_asos_uncased_en

* Add model 2024-09-20-trainerh2_pipeline_en

* Add model 2024-09-16-xlm_roberta_base_finetuned_panx_german_nadle_pipeline_en

* Add model 2024-09-23-mt5_base_visp_s2_pipeline_en

* Add model 2024-09-21-bert_vllm_gemma2b_llmoversight_0_5_nodropsus_1_en

* Add model 2024-09-18-roberta_nli_group71_pipeline_en

* Add model 2024-09-22-distilbert_base_uncased_finetuned_clinc_jnwulff_pipeline_en

* Add model 2024-09-13-sent_rubiobert_en

* Add model 2024-09-18-distilbert_base_uncased_finetuned_emotion_uisikdag_en

* Add model 2024-09-21-distilbert_base_uncased_banking_zphr_0st72_ut72ut7_plain_simsp_clean_en

* Add model 2024-09-16-distilbert_base_uncased_finetuned_squad_keerthana12_pipeline_en

* Add model 2024-09-22-distilbert_base_uncased_finetuned_nlp_letters_s1_s2_degendered_class_weighted_pipeline_en

* Add model 2024-09-17-robbert_2023_dutch_large_ft_lcn_actua_pipeline_en

* Add model 2024-09-19-distilbert_base_uncased_finetuned_emotions_jjfumero_pipeline_en

* Add model 2024-09-23-withinapps_ndd_mantisbt_test_tags_en

* Add model 2024-09-23-detector_god2_en

* Add model 2024-09-22-bert_base_uncased_finetune_squad_ep_0_9_lr_1e_05_wd_0_001_dp_0_99999_swati_70000_en

* Add model 2024-09-23-bert_base_cased_squad2_finetuned_squad_chocolatehog_en

* Add model 2024-09-20-uned_tfg_08_56_en

* Add model 2024-09-18-finace_nepal_bhasa_en

* Add model 2024-09-22-imdb_5_pipeline_en

* Add model 2024-09-20-roberta_base_bne_finetuned_detests_wandb24_pipeline_en

* Add model 2024-09-20-bert_fromscratch_galician_xlarge_pipeline_en

* Add model 2024-09-22-classification_model_pipeline_en

* Add model 2024-09-09-burmese_awesome_qa_model_acezxn_en

* Add model 2024-09-23-sent_bert_base_theseus_bulgarian_bg

* Add model 2024-09-11-roberta_large_few_shot_k_256_finetuned_squad_seed_0_pipeline_en

* Add model 2024-09-23-sent_dajobbert_base_uncased_pipeline_da

* Add model 2024-09-23-sent_bert_base_uncased_finetuned_news_1929_1932_en

* Add model 2024-09-23-sent_bert_political_election2020_twitter_mlm_en

* Add model 2024-09-23-sent_bert_political_election2020_twitter_mlm_pipeline_en

* Add model 2024-09-18-tibetan_roberta_g_v1_867238_en

* Add model 2024-09-23-sent_bert_large_cased_sigir_support_refute_norwegian_label_40_2nd_test_lr10_8_fast_8_en

* Add model 2024-09-23-sent_bert_base_cased_scmedium_en

* Add model 2024-09-23-sent_bert_base_cased_portuguese_lenerbr_alynneoya_en

* Add model 2024-09-23-sent_bert_base_cased_scmedium_pipeline_en

* Add model 2024-09-23-sent_twitch_bert_base_cased_pytorch_pipeline_en

* Add model 2024-09-23-sent_bert_finetuning_test_xiejiafang_pipeline_en

* Add model 2024-09-23-sent_bert_finetuning_test_xiejiafang_en

* Add model 2024-09-19-n_roberta_imdb_padding90model_en

* Add model 2024-09-18-distilbert_toxicity_classification_pipeline_en

* Add model 2024-09-22-bodo_roberta_base_sentencepiece_mlm_en

* Add model 2024-09-20-roberta_base_polyglotner_en

* Add model 2024-09-21-distilbert_base_uncased_finetuned_emotion_jiogenes_en

* Add model 2024-09-13-whisper_small_hindi_sanchit_gandhi_hi

* Add model 2024-09-23-distilbert_base_uncased_finetuned_emotion_cereline_pipeline_en

* Add model 2024-09-22-distilbert_base_uncased_sst2_v0_pipeline_en

* Add model 2024-09-19-whisper_small_arabic_noise2_pipeline_en

* Add model 2024-09-19-distilkobert_ep2_en

* Add model 2024-09-15-distilbert_base_spanish_cased_autext_pipeline_en

* Add model 2024-09-23-odiaberta_pipeline_en

* Add model 2024-09-21-whisper_small_english_mskov_pipeline_en

* Add model 2024-09-23-bert_base_uncase_conll2012_en

* Add model 2024-09-23-hindi_bpe_bert_test_2m_pipeline_en

* Add model 2024-09-20-stereotype_italian_it

* Add model 2024-09-20-burmese_awesome_model_gamdalf_pipeline_en

* Add model 2024-09-22-roberta_large_mnli_model3_en

* Add model 2024-09-18-distilbert_base_uncased_odm_zphr_0st5sd_ut72ut5_plprefix0stlarge_simsp100_clean200_en

* Add model 2024-09-08-opus_maltese_english_spanish_finetuned_spanish_tonga_tonga_islands_pbb_v2_en

* Add model 2024-09-16-all_roberta_large_v1_travel_7_16_5_en

* Add model 2024-09-22-jerteh355sentpos6_pipeline_en

* Add model 2024-09-21-ft_english_10maa_en

* Add model 2024-09-20-prueba_en

* Add model 2024-09-21-inlegalbert_pipeline_en

* Add model 2024-09-22-whisper_small_yoruba_omoekan_en

* Add model 2024-09-22-finetuned_sentiment_model_imdb_distilbert_2_pipeline_en

* Add model 2024-09-11-craft_bionlp_roberta_base_en

* Add model 2024-09-21-2020_q1_75p_filtered_random_en

* Add model 2024-09-22-bert_base_uncased_ep_3_11_b_32_lr_4e_06_dp_0_1_swati_700_southern_sotho_false_fh_true_hs_0_en

* Add model 2024-09-20-burmese_awesome_model_priority_3_pipeline_en

* Add model 2024-09-19-financial_sentiment_distilbert_en

* Add model 2024-09-22-bert_finetuned_swag_pipeline_en

* Add model 2024-09-23-burmese_awesome_model_nandini54_en

* Add model 2024-09-22-tiny_english_combined_v3_trimmed_1_0_15_8_1e_05_dainty_sweep_13_pipeline_en

* Add model 2024-09-13-pubchem10m_smiles_bpe_396_250_pipeline_en

* Add model 2024-09-23-sungbeom_whisper_small_korean_set31_ko

* Add model 2024-09-23-whisper_small_hindi_reach_vb_en

* Add model 2024-09-23-whisper_small_hindi_reach_vb_pipeline_en

* Add model 2024-09-21-whisper_small_bengali_shamik_bn

* Add model 2024-09-23-whisper_small_np_en

* Add model 2024-09-23-lab2_whisper_swedish_pipeline_hi

* Add model 2024-09-23-whisper_small_np_pipeline_en

* Add model 2024-09-23-whisper_tiny_aug_on_fly_pipeline_en

* Add model 2024-09-23-whisper_tiny_aug_on_fly_en

* Add model 2024-09-22-roberta_base_oscar_chen_en

* Add model 2024-09-18-sent_greeksocialbert_base_greek_uncased_v1_el

* Add model 2024-09-23-mobilebert_imdb_pipeline_en

* Add model 2024-09-19-xlm_roberta_base_finetuned_panx_french_occupy1_en

* Add model 2024-09-23-whisper_small_divehi_shahukareem_pipeline_dv

* Add model 2024-09-23-phowhisper_small_pipeline_vi

* Add model 2024-09-23-sent_bert_base_theseus_bulgarian_pipeline_bg

* Add model 2024-09-08-xtremedistil_l6_h256_uncased_pipeline_en

* Add model 2024-09-23-sent_bert_tiny_finetuned_legal_definitions_en

* Add model 2024-09-18-coha1980s_en

* Add model 2024-09-22-sent_indobert_base_p2_finetuned_mer_80k_en

* Add model 2024-09-23-whisper_ai_nomi_en

* Add model 2024-09-23-qa_model_gigazinie_pipeline_en

* Add model 2024-09-21-distilbert_base_uncased_finetuned_adl_hw1_penguinyeh_en

* Add model 2024-09-19-distilroberta_rb156k_opt15_ep40_en

* Add model 2024-09-23-whisper_tiny_hebrew_modern_2_he

* Add model 2024-09-16-opus_maltese_german_icelandic_finetuned_german_tonga_tonga_islands_icelandic_nr2_en

* Add model 2024-09-23-whisper_small_tonga_tonga_islands_chuvash_albanian_sq

* Add model 2024-09-17-question_answearing_7_distillbert_pipeline_en

* Add model 2024-09-23-burmese_awesome_model_eyeonyou_en

* Add model 2024-09-20-roberta_base_finetuned_wallisian_manual_8ep_pipeline_en

* Add model 2024-09-23-whisper_small_basque_xezpeleta_eu

* Add model 2024-09-17-sent_dictabert_tiny_pipeline_he

* Add model 2024-09-23-whisper_small_basque_xezpeleta_pipeline_eu

* Add model 2024-09-20-distilbert_sanskrit_saskta_glue_experiment_cola_384_en

* Add model 2024-09-10-bert_gemma_strongoversight_vllm_0_pipeline_en

* Add model 2024-09-23-whisper_small_mongolian_cafet_mn

* Add model 2024-09-23-whisper_small_mongolian_cafet_pipeline_mn

* Add model 2024-09-20-kinyaroberta_large_kinte_finetuned_kinyarwanda_tweet_finetuned_kinyarwanda_sent2_en

* Add model 2024-09-22-sent_banglabert_generator_pipeline_bn

* Add model 2024-09-21-roberta_base_epoch_47_en

* Add model 2024-09-17-xlm_roberta_base_ukraine_waray_philippines_pov_v1_en

* Add model 2024-09-23-bsc_bio_ehr_spanish_symptemist_word2vec_85_ner_pipeline_en

* Add model 2024-09-20-affilgood_ner_test_v4_en

* Add model 2024-09-19-alberta_base_nbolton04_en

* Add model 2024-09-23-bert_base_uncased_finetuned_mrpc_w05230505_pipeline_en

* Add model 2024-09-19-cv9_special_batch8_lr6_small_pipeline_id

* Add model 2024-09-20-question_classification_minervabotteam_en

* Add model 2024-09-21-whisper_tiny_frenchmed_v1_pipeline_fr

* Add model 2024-09-20-xlm_roberta_base_finetuned_panx_german_french_zardian_en

* Add model 2024-09-23-whisper_small_ar2_ar

---------

Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>
  • Loading branch information
@jsl-models @ahmedlone127
jsl-models and ahmedlone127 authored Sep 23, 2024
1 parent 884d929 commit 5c0b554
Show file tree
Hide file tree
Showing 1,821 changed files with 148,396 additions and 0 deletions.
71 changes: 71 additions & 0 deletions ...posts/ahmedlone127/2024-09-04-sent_bert_base_spanish_wwm_uncased_pipeline_es.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
---
layout: model
title: Castilian, Spanish sent_bert_base_spanish_wwm_uncased_pipeline pipeline BertSentenceEmbeddings from dccuchile
author: John Snow Labs
name: sent_bert_base_spanish_wwm_uncased_pipeline
date: 2024-09-04
tags: [es, open_source, pipeline, onnx]
task: Embeddings
language: es
edition: Spark NLP 5.5.0
spark_version: 3.0
supported: true
annotator: PipelineModel
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained BertSentenceEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`sent_bert_base_spanish_wwm_uncased_pipeline` is a Castilian, Spanish model originally trained by dccuchile.

{:.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/sent_bert_base_spanish_wwm_uncased_pipeline_es_5.5.0_3.0_1725415961164.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/sent_bert_base_spanish_wwm_uncased_pipeline_es_5.5.0_3.0_1725415961164.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("sent_bert_base_spanish_wwm_uncased_pipeline", lang = "es")
annotations = pipeline.transform(df)

```
```scala

val pipeline = new PretrainedPipeline("sent_bert_base_spanish_wwm_uncased_pipeline", lang = "es")
val annotations = pipeline.transform(df)

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|sent_bert_base_spanish_wwm_uncased_pipeline|
|Type:|pipeline|
|Compatibility:|Spark NLP 5.5.0+|
|License:|Open Source|
|Edition:|Official|
|Language:|es|
|Size:|410.2 MB|

## References

https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased

## Included Models

- DocumentAssembler
- TokenizerModel
- SentenceDetectorDLModel
- BertSentenceEmbeddings
86 changes: 86 additions & 0 deletions docs/_posts/ahmedlone127/2024-09-05-qa_synthetic_data_only_finetuned_v1_0_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,86 @@
---
layout: model
title: English qa_synthetic_data_only_finetuned_v1_0 XlmRoBertaForQuestionAnswering from am-infoweb
author: John Snow Labs
name: qa_synthetic_data_only_finetuned_v1_0
date: 2024-09-05
tags: [en, open_source, onnx, question_answering, xlm_roberta]
task: Question Answering
language: en
edition: Spark NLP 5.5.0
spark_version: 3.0
supported: true
engine: onnx
annotator: XlmRoBertaForQuestionAnswering
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained XlmRoBertaForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`qa_synthetic_data_only_finetuned_v1_0` is a English model originally trained by am-infoweb.

{:.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/qa_synthetic_data_only_finetuned_v1_0_en_5.5.0_3.0_1725557042495.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/qa_synthetic_data_only_finetuned_v1_0_en_5.5.0_3.0_1725557042495.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 = MultiDocumentAssembler() \
.setInputCol(["question", "context"]) \
.setOutputCol(["document_question", "document_context"])

spanClassifier = XlmRoBertaForQuestionAnswering.pretrained("qa_synthetic_data_only_finetuned_v1_0","en") \
.setInputCols(["document_question","document_context"]) \
.setOutputCol("answer")

pipeline = Pipeline().setStages([documentAssembler, spanClassifier])
data = spark.createDataFrame([["What framework do I use?","I use spark-nlp."]]).toDF("document_question", "document_context")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)

```
```scala

val documentAssembler = new MultiDocumentAssembler()
.setInputCol(Array("question", "context"))
.setOutputCol(Array("document_question", "document_context"))

val spanClassifier = XlmRoBertaForQuestionAnswering.pretrained("qa_synthetic_data_only_finetuned_v1_0", "en")
.setInputCols(Array("document_question","document_context"))
.setOutputCol("answer")

val pipeline = new Pipeline().setStages(Array(documentAssembler, spanClassifier))
val data = Seq("What framework do I use?","I use spark-nlp.").toDS.toDF("document_question", "document_context")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|qa_synthetic_data_only_finetuned_v1_0|
|Compatibility:|Spark NLP 5.5.0+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[document_question, document_context]|
|Output Labels:|[answer]|
|Language:|en|
|Size:|803.6 MB|

## References

https://huggingface.co/am-infoweb/QA_SYNTHETIC_DATA_ONLY_Finetuned_v1.0
94 changes: 94 additions & 0 deletions docs/_posts/ahmedlone127/2024-09-06-claim_extraction_classifier_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
---
layout: model
title: English claim_extraction_classifier DeBertaForSequenceClassification from KnutJaegersberg
author: John Snow Labs
name: claim_extraction_classifier
date: 2024-09-06
tags: [en, open_source, onnx, sequence_classification, deberta]
task: Text Classification
language: en
edition: Spark NLP 5.5.0
spark_version: 3.0
supported: true
engine: onnx
annotator: DeBertaForSequenceClassification
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

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

{:.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/claim_extraction_classifier_en_5.5.0_3.0_1725611976387.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/claim_extraction_classifier_en_5.5.0_3.0_1725611976387.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}

## How to use



<div class="tabs-box" markdown="1">
{% include programmingLanguageSelectScalaPythonNLU.html %}
```python

documentAssembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')

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

sequenceClassifier = DeBertaForSequenceClassification.pretrained("claim_extraction_classifier","en") \
.setInputCols(["documents","token"]) \
.setOutputCol("class")

pipeline = Pipeline().setStages([documentAssembler, tokenizer, sequenceClassifier])
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 tokenizer = new Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")

val sequenceClassifier = DeBertaForSequenceClassification.pretrained("claim_extraction_classifier", "en")
.setInputCols(Array("documents","token"))
.setOutputCol("class")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier))
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:|claim_extraction_classifier|
|Compatibility:|Spark NLP 5.5.0+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[document, token]|
|Output Labels:|[class]|
|Language:|en|
|Size:|1.5 GB|

## References

https://huggingface.co/KnutJaegersberg/claim_extraction_classifier
94 changes: 94 additions & 0 deletions docs/_posts/ahmedlone127/2024-09-07-bert_wnut_token_classifier_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
---
layout: model
title: English bert_wnut_token_classifier DistilBertForTokenClassification from ZappY-AI
author: John Snow Labs
name: bert_wnut_token_classifier
date: 2024-09-07
tags: [en, open_source, onnx, token_classification, distilbert, ner]
task: Named Entity Recognition
language: en
edition: Spark NLP 5.5.0
spark_version: 3.0
supported: true
engine: onnx
annotator: DistilBertForTokenClassification
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained DistilBertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_wnut_token_classifier` is a English model originally trained by ZappY-AI.

{:.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/bert_wnut_token_classifier_en_5.5.0_3.0_1725729872514.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_wnut_token_classifier_en_5.5.0_3.0_1725729872514.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}

## How to use



<div class="tabs-box" markdown="1">
{% include programmingLanguageSelectScalaPythonNLU.html %}
```python

documentAssembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')

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

tokenClassifier = DistilBertForTokenClassification.pretrained("bert_wnut_token_classifier","en") \
.setInputCols(["documents","token"]) \
.setOutputCol("ner")

pipeline = Pipeline().setStages([documentAssembler, tokenizer, tokenClassifier])
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 tokenizer = new Tokenizer()
.setInputCols("document")
.setOutputCol("token")

val tokenClassifier = DistilBertForTokenClassification.pretrained("bert_wnut_token_classifier", "en")
.setInputCols(Array("documents","token"))
.setOutputCol("ner")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, tokenClassifier))
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:|bert_wnut_token_classifier|
|Compatibility:|Spark NLP 5.5.0+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[document, token]|
|Output Labels:|[ner]|
|Language:|en|
|Size:|247.3 MB|

## References

https://huggingface.co/ZappY-AI/bert-wnut-token-classifier
Loading

0 comments on commit 5c0b554

Please sign in to comment.