Skip to content

Commit

Permalink
2024-09-19-ner_chunkyun_pipeline_en (#14404)
Browse files Browse the repository at this point in the history 
* Add model 2024-09-16-nykaa_sentiment_model_distilbert_pipeline_en

* Add model 2024-09-19-roberta_large_full_finetuned_ner_single_en

* Add model 2024-09-19-2020_q4_75p_filtered_random_pipeline_en

* Add model 2024-09-19-distilbert_base_uncased_finetuned_sanskrit_saskta_en

* Add model 2024-09-20-burmese_awesome_qa_model_balchid_en

* Add model 2024-09-20-burmese_awesome_qa_model_balchid_pipeline_en

* Add model 2024-09-19-article_sentiment_analysis_model_en

* Add model 2024-09-20-rinna_roberta_qa_ar101_pipeline_en

* Add model 2024-09-09-distilbert_finetuned_squadv2_hungmanh6401_pipeline_en

* Add model 2024-09-19-conflibert_scr_cased_pipeline_en

* Add model 2024-09-18-xlm_roberta_base_nepal_bhasa_vietnam_aug_insert_synonym_pipeline_en

* Add model 2024-09-20-roberta_finetuned_subjqa_movies_2_francisca28_en

* Add model 2024-09-20-dfm_ed3_en

* Add model 2024-09-12-deberta_v3_large_llmmdlprefold_60k_20_09_2023_0_en

* Add model 2024-09-17-xlm_roberta_base_finetuned_panx_italian_u00890358_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_emotion_nieche2_en

* Add model 2024-09-20-distilbert_base_uncased_odm_zphr_0st14sd_ut72ut1large14pfxnf_simsp400_clean100_en

* Add model 2024-09-20-nepal_bhasa_dummy_model_thewitcher_en

* Add model 2024-09-20-burmese_awesome_model_s_kinoshita_pipeline_en

* Add model 2024-09-20-burmese_awesome_model_diodiodada_pipeline_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_cola_matthewchung74_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_emotion_btown2_en

* Add model 2024-09-20-distilbert_stackoverflow_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_sst_2_english_finetuned_abstract_classification_en

* Add model 2024-09-20-movie_genre_multi_classification_en

* Add model 2024-09-17-lingala_japanese_english_helsinki_en

* Add model 2024-09-20-wannasleep_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_cola_rubensmau_en

* Add model 2024-09-19-test7_balanced_and_sentence_pipeline_en

* Add model 2024-09-16-whisper_small_punjabi_eastern_in_pipeline_pa

* Add model 2024-09-13-output_htm_2_fpdm_roberta_pipeline_en

* Add model 2024-09-20-sanskrit_saskta_roberta_e3_w1_5_b16_w0_01_data2_en

* Add model 2024-09-20-roberta_base_ag_news_aktsvigun_pipeline_en

* Add model 2024-09-20-geofin2_en

* Add model 2024-09-18-distilbert_base_uncased_finetuned_emotions_jjwariror_pipeline_en

* Add model 2024-09-18-xlm_roberta_base_finetuned_panx_german_french_youngbeauty_en

* Add model 2024-09-15-whisper_small_paula_pipeline_en

* Add model 2024-09-19-cold_fusion_itr25_seed1_en

* Add model 2024-09-20-xlm_v_base_xnli_french_trimmed_french_pipeline_en

* Add model 2024-09-18-burmese_awesome_model_jayhook_en

* Add model 2024-09-17-marian_finetuned_kde4_english_tonga_tonga_islands_french_chinonyelum_pipeline_en

* Add model 2024-09-18-distilbert_sanskrit_saskta_glue_experiment_logit_kd_data_aug_sst2_256_en

* Add model 2024-09-11-roberta_base_finetuned_vedantgaur_human_generated_en

* Add model 2024-09-19-pubchem10m_smiles_bpe_450k_pipeline_en

* Add model 2024-09-19-roberta_base_finetuned_mp_unannotated_half_frozen_v1_rile_v1_frozen_8_en

* Add model 2024-09-20-sci_sentiment_classify_en

* Add model 2024-09-20-convbert_base_generator_finnish_fi

* Add model 2024-09-18-absa_restaurant_froberta_base_v0_en

* Add model 2024-09-18-agriculture_classification_zh

* Add model 2024-09-18-distilbert_base_uncased_finetuned_emotion_helloyeew_pipeline_en

* Add model 2024-09-17-incremental_semi_supervised_training_500k_downsampled_en

* Add model 2024-09-15-whisper_small_ukrainian_nikes64_pipeline_uk

* Add model 2024-09-05-seq2seq_finetuned_cxg_dutch_tonga_tonga_islands_code_en

* Add model 2024-09-17-distilbert_emotion_emrahgunes_en

* Add model 2024-09-15-marta_t5_gpt_en

* Add model 2024-09-20-roberta_recipes_pipeline_en

* Add model 2024-09-16-finetuned_model_mellowpont_en

* Add model 2024-09-18-distilbert_sanskrit_saskta_glue_experiment_logit_kd_stsb_192_en

* Add model 2024-09-19-distilbert_base_uncased_odm_zphr_0st19sd_ut72ut5_plprefix0stlarge19_simsp100_clean300_pipeline_en

* Add model 2024-09-17-xlm_roberta_base_finetuned_panx_german_french_monkdalma_pipeline_en

* Add model 2024-09-20-whisper_tiny_us_agercas_en

* Add model 2024-09-20-whisper_small_oriya_bn

* Add model 2024-09-18-demo_model_tanmoyeeroy_en

* Add model 2024-09-18-roberta_dnd_intents_pipeline_en

* Add model 2024-09-14-albert_large_v2_finetuned_mrpc_vitaliivrublevskyi_pipeline_en

* Add model 2024-09-18-2020_q4_full_tweets_pipeline_en

* Add model 2024-09-19-distalbert_arabic_classification_pipeline_en

* Add model 2024-09-19-finetuning_sentiment_model_3000_samples_8_en

* Add model 2024-09-19-distilbert_sanskrit_saskta_glue_experiment_logit_kd_wnli_96_en

* Add model 2024-09-20-flattery_prediction_text_pipeline_en

* Add model 2024-09-17-distilbert_finetuned_squadv2_vietdo26_pipeline_en

* Add model 2024-09-20-hf_qa_bert_base_uncased_en

* Add model 2024-09-17-whisper_base_jyutping_without_tones_full_merged_pipeline_en

* Add model 2024-09-19-bert_l12_h256_uncased_en

* Add model 2024-09-20-whisper_tiny_galician_gl

* Add model 2024-09-17-roberta_base_finetuned_wallisian_manual_1ep_en

* Add model 2024-09-18-distilbert_yes_norwegian_other_intent_en

* Add model 2024-09-10-gal_enpt_xlm_r_gl

* Add model 2024-09-20-test2_pipeline_en

* Add model 2024-09-09-dbtest_trainer_pipeline_en

* Add model 2024-09-14-whisper_small_serbian_ri_en

* Add model 2024-09-20-checkpoint2_zh

* Add model 2024-09-17-xlm_roberta_base_finetuned_panx_german_french_wooihen_en

* Add model 2024-09-20-bert_based_uncased_sst2_e3_pipeline_en

* Add model 2024-09-20-scenario_non_kd_scr_d2_data_amazonscience_massive_all_1_1111_en

* Add model 2024-09-19-distilbert_base_uncased_finetuned_document_pipeline_en

* Add model 2024-09-05-secdisclosure_28l_en

* Add model 2024-09-20-xlm_roberta_base_finetuned_marc_agudden_en

* Add model 2024-09-17-protein_custom_model_veresnoemi_en

* Add model 2024-09-20-whisper_small_hindi_rishabbahal_hi

* Add model 2024-09-15-simpletransformer_qa_roberta_base_mtanzi_hopin_en

* Add model 2024-09-19-roberta_base_epoch_59_en

* Add model 2024-09-20-wablab2_sv

* Add model 2024-09-20-whisper_small_hindi_rishabbahal_pipeline_hi

* Add model 2024-09-20-wablab2_pipeline_sv

* Add model 2024-09-20-burmese_idea_classification_model_trial_1_en

* Add model 2024-09-08-stego_classifier_checkpoint_epoch_80_2024_07_26_16_03_28_pipeline_en

* Add model 2024-09-20-burmese_awesome_model_imdb_en

* Add model 2024-09-15-trainer_chapter4_pbwauyo_pipeline_en

* Add model 2024-09-20-finetuning_sentiment_model_3000_samples_naomaru_en

* Add model 2024-09-20-all_roberta_large_v1_banking_1000_16_5_oos_pipeline_en

* Add model 2024-09-20-whisper_small_breton_pipeline_en

* Add model 2024-09-20-openai_whisper_tiny_spanish_ecu911_pasobajo_es

* Add model 2024-09-20-distilbert_base_uncased_odm_zphr_odm_zphr_0st102sd_random_ut72ut1_plprefix0stlarge_simsp100_en

* Add model 2024-09-20-whisper_tiny_divehi_hwhjones_pipeline_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_sst_2_english_finetuned_abstract_classification_pipeline_en

* Add model 2024-09-20-whisper_tiny_divehi_hwhjones_en

* Add model 2024-09-18-distilbert_base_uncased_travel_zphr_0st_ut52ut5_plainvalprefixlora_simsp_clean_en

* Add model 2024-09-17-xlm_roberta_base_finetuned_panx_all_smilingface88_pipeline_en

* Add model 2024-09-15-finetuning_distilbert_model_steam_game_reviews_pipeline_en

* Add model 2024-09-20-text_classification_linsad_pipeline_en

* Add model 2024-09-20-tmp_date_en

* Add model 2024-09-20-sent_bert_base_uncased_issues_128_phnghiapro_pipeline_en

* Add model 2024-09-20-sent_bert_base_historic_english_cased_en

* Add model 2024-09-20-sent_bert_base_historic_english_cased_pipeline_en

* Add model 2024-09-11-distilbert_base_uncased_finetuned_squad_taytaychu_en

* Add model 2024-09-20-sent_bert_base_uncased_sparse_85_unstructured_pruneofa_en

* Add model 2024-09-18-divya_resume_model_en

* Add model 2024-09-20-sent_finest_bert_pipeline_fi

* Add model 2024-09-20-qatentbert_cpc_pipeline_en

* Add model 2024-09-13-whisper_small_cantonese_oblivion208_en

* Add model 2024-09-09-cino_small_v2_tncc_document_tsheg_en

* Add model 2024-09-19-burmese_distillbert_model2_pipeline_en

* Add model 2024-09-18-bert_base_uncased_finetuned_skydata_en

* Add model 2024-09-18-burmese_awesome_qa_model_ashishkj23_en

* Add model 2024-09-18-elicitsbackgroundknowledge_a6000_0_00001_en

* Add model 2024-09-20-roberta_base_research_papers_en

* Add model 2024-09-17-indicbertv2_mlm_sam_tlm_ner_pipeline_nan

* Add model 2024-09-17-text_classification_thirdeyedata_en

* Add model 2024-09-20-roberta_bert_10_en

* Add model 2024-09-20-minilm_l6_v2_en

* Add model 2024-09-20-minilm_l6_v2_pipeline_en

* Add model 2024-09-20-colombian_sign_language_small_unbiased_random_20_pipeline_en

* Add model 2024-09-18-twitter_roberta_base_sentiment_fine_tuned_en

* Add model 2024-09-20-mlm_pretrain_model_en

* Add model 2024-09-20-output_en

* Add model 2024-09-20-distilroberta_base_ep20_pipeline_en

* Add model 2024-09-09-gottbert_base_uklfr_en

* Add model 2024-09-20-roberta_codesearchnet_nepal_bhasa_pipeline_en

* Add model 2024-09-20-icebert_igc_pipeline_is

* Add model 2024-09-11-burmese_awesome_opus_books_model_lucasschnee_pipeline_en

* Add model 2024-09-19-roberta_large_earnings21_non_normalized_en

* Add model 2024-09-17-qa_finetuned_distilbert_based_uncased_ar

* Add model 2024-09-19-hatebertimbau_pipeline_pt

* Add model 2024-09-19-distilbert_sentiment140_en

* Add model 2024-09-16-opus_maltese_english_ganda_finetuned_english_tonga_tonga_islands_ganda_achuka_pipeline_en

* Add model 2024-09-14-regression_xlm_roberta_divemt_ita_pipeline_en

* Add model 2024-09-19-roberta_large_finetuned_abbr_unfiltered_plod_en

* Add model 2024-09-19-japanese_fine_tuned_whisper_model_nikolajvestergaard_pipeline_ja

* Add model 2024-09-18-roberta_baseline_finetuned_atis_3pct_v0_pipeline_en

* Add model 2024-09-10-distilbert_on_yelp_reviews_full_epoch_2_en

* Add model 2024-09-20-stress_mentalbert_en

* Add model 2024-09-16-danish_roberta_babe_ft_pipeline_en

* Add model 2024-09-17-xlm_roberta_base_finetuned_panx_french_mjqing_en

* Add model 2024-09-20-checkpoint2_pipeline_zh

* Add model 2024-09-18-xlm_roberta_base_xnli_french_trimmed_french_15000_en

* Add model 2024-09-17-xlm_roberta_base_finetuned_panx_german_takapy_pipeline_en

* Add model 2024-09-20-bert_base_banking77_pt2_saeed7272_pipeline_en

* Add model 2024-09-18-fake_news_detect_pipeline_en

* Add model 2024-09-10-dataequity_opus_maltese_arabic_english_en

* Add model 2024-09-15-autotrain_qa_user_954831770_pipeline_en

* Add model 2024-09-18-distilbert_base_uncased_finetuned_squad_alexcoliveira_pipeline_en

* Add model 2024-09-13-bert_large_uncased_sst2_en

* Add model 2024-09-18-englishessay_scoring_lm_en

* Add model 2024-09-17-whisper_base_chuvash_highlr_czech_pipeline_cs

* Add model 2024-09-06-distilbert_base_uncased_finetuned_goemotion_pipeline_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_imdb_h40vv3n_pipeline_en

* Add model 2024-09-19-roberta_base_epoch_61_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_emotion_minsu_chae_en

* Add model 2024-09-16-marianmix_english_japanese_10_en

* Add model 2024-09-19-roberta_finetuned_parsi_mianeh_corpus_nan

* Add model 2024-09-20-whisper_small_yue_chinese_hk_retrained_1_pipeline_en

* Add model 2024-09-18-sentiment_roberta_large_e12_b16_en

* Add model 2024-09-20-whisper_tiny_tamil_hi

* Add model 2024-09-18-distilbert_base_uncased_finetuned_clinc_leesihyun_pipeline_en

* Add model 2024-09-18-results_nelsonauner_en

* Add model 2024-09-18-sent_bert_base_english_arabic_cased_en

* Add model 2024-09-20-llm_b_hw001_en

* Add model 2024-09-10-fine_tuned_mpnetv2_en

* Add model 2024-09-15-multi_label_class_classification_on_github_issues_en

* Add model 2024-09-15-whisper_asr_atc_v5_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_emotion_nieche2_pipeline_en

* Add model 2024-09-18-xlm_roberta_base_mixed_origin_pipeline_en

* Add model 2024-09-20-distilbert_base_uncased_finetuned_cola_matthewchung74_pipeline_en

* Add model 2024-09-18-distilbert_base_uncased_finetuned_squad_sanghakoh_en

* Add model 2024-09-18-bert_base_uncased_issues_128_takaiwai_en

* Add model 2024-09-20-sanskrit_saskta_roberta_e3_w1_5_b16_w0_01_data2_pipeline_en

* Add model 2024-09-20-text_classification_linsad_en

* Add model 2024-09-20-geofin2_pipeline_en

* Add model 2024-09-20-schemeclassifier_esp_pipeline_en

* Add model 2024-09-13-somd_train_xlm_v3_pipeline_en

* Add model 2024-09-19-iab_category_classification_en

* Add model 2024-09-19-sent_aethiqs_gembert_bertje_50k_en

* Add model 2024-09-19-sent_finbert_pretrain_financeinc_pipeline_en

* Add model 2024-09-16-helsinki_danish_swedish_v5_en

* Add model 2024-09-20-roberta_base_research_papers_pipeline_en

* Add model 2024-09-18-distilbert_sanskrit_saskta_glue_experiment_logit_kd_data_aug_sst2_256_pipeline_en

* Add model 2024-09-19-korean_clickbait_news_classifier_xlm_roberta_base_en

* Add model 2024-09-15-babyberta_wikipedia_french_wikipedia1_2_5m_without_masking_seed6_finetuned_squad_pipeline_en

* Add model 2024-09-18-847_capstone_tweets_bert_v2_pipeline_en

* Add model 2024-09-14-opus_maltese_arabic_english_finetuned_arabic_tonga_tonga_islands_english_elnasharomar2_en

* Add model 2024-09-18-lao_roberta_base_lo

* Add model 2024-09-17-distilbert_base_cased_logdetective_extraction_retrained_jpodivin_pipeline_en

* Add model 2024-09-20-legal_undedup_base_v1_5__checkpoint_2_50000_pipeline_en

* Add model 2024-09-20-legal_undedup_base_v1_5__checkpoint_2_50000_en

* Add model 2024-09-20-roberta_bert_10_pipeline_en

* Add model 2024-09-20-brwac_v1_5__checkpoint_last_en

* Add model 2024-09-10-multilingual_e5_base_finetuned_cola_xx

* Add model 2024-09-20-output_pipeline_en

* Add model 2024-09-20-brwac_v1_5__checkpoint_last_pipeline_en

* Add model 2024-09-16-opus_maltese_ft_5_pipeline_en

* Add model 2024-09-07-xlm_roberta_base_finetuned_panx_all_wendao_123_pipeline_en

* Add model 2024-09-19-spa_xlm_r_es

* Add model 2024-09-17-twitter_data_xlm_roberta_base_eng_only_sentiment_finetuned_memes_pipeline_en

* Add model 2024-09-19-code_search_trained_base_random_trimmed_with_g_2_pipeline_en

* Add model 2024-09-17-hfa_poly_english_small_en

* Add model 2024-09-19-furina_seed42_eng_esp_hau_basic_5e_06_pipeline_en

* Add model 2024-09-18-trainranker_test_test_en

* Add model 2024-09-15-scenario_tcr_4_data_cardiffnlp_tweet_sentiment_multilingual_all_xx

* Add model 2024-09-11-ibert_roberta_base_finetuned_mrpc_en

* Add model 2024-09-18-transfomer_preds_en

* Add model 2024-09-17-bert_clf_results_andyrasika_pipeline_en

* Add model 2024-09-10-xlm_roberta_base_misogyny_sexism_tweets_en

* Add model 2024-09-19-burmese_awesome_qa_model_lwq1010_pipeline_en

* Add model 2024-09-19-roberta_finetuned_ner_longforms_pipeline_en

* Add model 2024-09-17-xlm_roberta_base_finetuned_panx_arabic_roaaoal_en

* Add model 2024-09-20-xlm_roberta_base_finetuned_marc_agudden_pipeline_en

* Add model 2024-09-17-xlm_roberta_base_finetuned_ud_arabic_ar

* Add model 2024-09-18-xlm_roberta_base_trimmed_spanish_60000_tweet_sentiment_spanish_en

* Add model 2024-09-19-finetuning_sentiment_model_40000_movie_reviews_sample_1_en

* Add model 2024-09-20-roberta_finetuned_subjqa_movies_2_francisca28_pipeline_en

* Add model 2024-09-16-440fc6ae_75a5_4a7e_a238_65e06e620a59_pipeline_en

* Add model 2024-09-19-distilbert_base_multilingual_cased_actitud_german_tener_latin_razon_esp_xx

* Add model 2024-09-18-distilbert_emotions_fellowship_pipeline_en

* Add model 2024-09-18-sentiment_sentiment_small_random0_seed0_twitter_roberta_base_2021_124m_pipeline_en

* Add model 2024-09-15-whisper_small_urdu_aosaf_en

* Add model 2024-09-18-distilbert_base_uncased_finetuned_emotion_ujjwalgarg_pipeline_en

* Add model 2024-09-20-burmese_awesome_model_soosookentelmanis_pipeline_en

* Add model 2024-09-18-text_sentiment_analyse_en

* Add model 2024-09-15-testing_model_1_mikecho_en

* Add model 2024-09-17-albert_base_v2_finetuned_emotion_niktasadr98_pipeline_en

* Add model 2024-09-19-burmese_awesome_model_yjoonjang_pipeline_en

* Add model 2024-09-18-db_mc2_3_2_pipeline_en

* Add model 2024-09-18-distilbert_base_uncased_credit_cards_zphr_0st72_en

* Add model 2024-09-06-address_extraction_pipeline_tr

* Add model 2024-09-19-burmese_model_mahikajain_en

* Add model 2024-09-18-t_103_en

* Add model 2024-09-17-helsinki_danish_swedish_v8_en

* Add model 2024-09-14-finetuned_twitter_sentiment_roberta_en

* Add model 2024-09-18-roberta_base_finetuned_dow_en

---------

Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>
  • Loading branch information
@jsl-models @ahmedlone127
jsl-models and ahmedlone127 authored Sep 20, 2024
1 parent 2e32685 commit fef850d
Show file tree
Hide file tree
Showing 1,452 changed files with 117,891 additions and 0 deletions.
70 changes: 70 additions & 0 deletions docs/_posts/ahmedlone127/2024-09-02-koobert_pipeline_xx.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
---
layout: model
title: Multilingual koobert_pipeline pipeline BertEmbeddings from KooAI
author: John Snow Labs
name: koobert_pipeline
date: 2024-09-02
tags: [xx, open_source, pipeline, onnx]
task: Embeddings
language: xx
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 BertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`koobert_pipeline` is a Multilingual model originally trained by KooAI.

{:.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/koobert_pipeline_xx_5.5.0_3.0_1725318896545.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/koobert_pipeline_xx_5.5.0_3.0_1725318896545.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("koobert_pipeline", lang = "xx")
annotations = pipeline.transform(df)

```
```scala

val pipeline = new PretrainedPipeline("koobert_pipeline", lang = "xx")
val annotations = pipeline.transform(df)

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|koobert_pipeline|
|Type:|pipeline|
|Compatibility:|Spark NLP 5.5.0+|
|License:|Open Source|
|Edition:|Official|
|Language:|xx|
|Size:|689.1 MB|

## References

https://huggingface.co/KooAI/KooBERT

## Included Models

- DocumentAssembler
- TokenizerModel
- BertEmbeddings
70 changes: 70 additions & 0 deletions ...posts/ahmedlone127/2024-09-02-tweets_sentiment_model_60k_samples_pipeline_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
---
layout: model
title: English tweets_sentiment_model_60k_samples_pipeline pipeline DistilBertForSequenceClassification from ivanscorral
author: John Snow Labs
name: tweets_sentiment_model_60k_samples_pipeline
date: 2024-09-02
tags: [en, open_source, pipeline, onnx]
task: Text Classification
language: en
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 DistilBertForSequenceClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`tweets_sentiment_model_60k_samples_pipeline` is a English model originally trained by ivanscorral.

{:.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/tweets_sentiment_model_60k_samples_pipeline_en_5.5.0_3.0_1725305885755.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/tweets_sentiment_model_60k_samples_pipeline_en_5.5.0_3.0_1725305885755.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("tweets_sentiment_model_60k_samples_pipeline", lang = "en")
annotations = pipeline.transform(df)

```
```scala

val pipeline = new PretrainedPipeline("tweets_sentiment_model_60k_samples_pipeline", lang = "en")
val annotations = pipeline.transform(df)

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|tweets_sentiment_model_60k_samples_pipeline|
|Type:|pipeline|
|Compatibility:|Spark NLP 5.5.0+|
|License:|Open Source|
|Edition:|Official|
|Language:|en|
|Size:|249.5 MB|

## References

https://huggingface.co/ivanscorral/tweets-sentiment-model-60k-samples

## Included Models

- DocumentAssembler
- TokenizerModel
- DistilBertForSequenceClassification
70 changes: 70 additions & 0 deletions docs/_posts/ahmedlone127/2024-09-05-bert_full_finetuned_ner_pablo_pipeline_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
---
layout: model
title: English bert_full_finetuned_ner_pablo_pipeline pipeline BertForTokenClassification from pabRomero
author: John Snow Labs
name: bert_full_finetuned_ner_pablo_pipeline
date: 2024-09-05
tags: [en, open_source, pipeline, onnx]
task: Named Entity Recognition
language: en
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 BertForTokenClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_full_finetuned_ner_pablo_pipeline` is a English model originally trained by pabRomero.

{:.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_full_finetuned_ner_pablo_pipeline_en_5.5.0_3.0_1725538599406.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_full_finetuned_ner_pablo_pipeline_en_5.5.0_3.0_1725538599406.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("bert_full_finetuned_ner_pablo_pipeline", lang = "en")
annotations = pipeline.transform(df)

```
```scala

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

```
</div>

{:.model-param}
## Model Information

{:.table-model}
|---|---|
|Model Name:|bert_full_finetuned_ner_pablo_pipeline|
|Type:|pipeline|
|Compatibility:|Spark NLP 5.5.0+|
|License:|Open Source|
|Edition:|Official|
|Language:|en|
|Size:|407.3 MB|

## References

https://huggingface.co/pabRomero/BERT-full-finetuned-ner-pablo

## Included Models

- DocumentAssembler
- TokenizerModel
- BertForTokenClassification
94 changes: 94 additions & 0 deletions docs/_posts/ahmedlone127/2024-09-05-secdisclosure_28l_en.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
---
layout: model
title: English secdisclosure_28l RoBertaForSequenceClassification from EGAPE
author: John Snow Labs
name: secdisclosure_28l
date: 2024-09-05
tags: [en, open_source, onnx, sequence_classification, roberta]
task: Text Classification
language: en
edition: Spark NLP 5.5.0
spark_version: 3.0
supported: true
engine: onnx
annotator: RoBertaForSequenceClassification
article_header:
type: cover
use_language_switcher: "Python-Scala-Java"
---

## Description

Pretrained RoBertaForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`secdisclosure_28l` is a English model originally trained by EGAPE.

{:.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/secdisclosure_28l_en_5.5.0_3.0_1725541670119.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/secdisclosure_28l_en_5.5.0_3.0_1725541670119.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 = RoBertaForSequenceClassification.pretrained("secdisclosure_28l","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 = RoBertaForSequenceClassification.pretrained("secdisclosure_28l", "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:|secdisclosure_28l|
|Compatibility:|Spark NLP 5.5.0+|
|License:|Open Source|
|Edition:|Official|
|Input Labels:|[document, token]|
|Output Labels:|[class]|
|Language:|en|
|Size:|309.7 MB|

## References

https://huggingface.co/EGAPE/secdisclosure-28l
Loading

0 comments on commit fef850d

Please sign in to comment.