Skip to content

Dataset & Encoder refactoring #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
a0x8o wants to merge 8,966 commits into
base: master
Choose a base branch
from
Open

Dataset & Encoder refactoring #1

a0x8o wants to merge 8,966 commits into from

Conversation

@a0x8o
Copy link

@a0x8o a0x8o commented Jul 13, 2023

Description

Motivation and Context

How Has This Been Tested?

Screenshots (if appropriate):

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • Code improvements with no or little impact
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)

Checklist:

  • My code follows the code style of this project.
  • My change requires a change to the documentation.
  • I have updated the documentation accordingly.
  • I have read the CONTRIBUTING page.
  • I have added tests to cover my changes.
  • All new and existing tests passed.

DevinTDHa and others added 30 commits March 14, 2025 17:26
@DevinTDHa
Fix notebook error format
f3d353c
@maziyarpanahi
Merge pull request #14242 from JohnSnowLabs/SPARKNLP-1006-Implement-OLMo
05000ab 
SPARKNLP-1006: Introducing OLMo
@maziyarpanahi
Merge branch 'release/600-release-candidate' into SPARKNLP-1060-Imple…
6d71770 
…ment-Phi-3.5-Vision
@maziyarpanahi
Merge pull request #14444 from JohnSnowLabs/SPARKNLP-1060-Implement-P…
44fb92a 
…hi-3.5-Vision

Sparknlp 1060 implement phi 3.5 vision
@maziyarpanahi
Merge branch 'release/600-release-candidate' into SPARKNLP-1033-Imple…
f33ce00 
…ment-LLaVA-and-LLaVA-NeXT
@maziyarpanahi
Merge pull request #14450 from JohnSnowLabs/SPARKNLP-1033-Implement-L…
7b65030 
…LaVA-and-LLaVA-NeXT

SparkNLP 1033: Introducing LLAVA
@maziyarpanahi
Merge branch 'release/600-release-candidate' into SPARKNLP-1032-CoHere
92c7e12
@maziyarpanahi
Merge pull request #14457 from JohnSnowLabs/SPARKNLP-1032-CoHere
2c867de 
SparkNLP 1032: Introducing CoHere
@maziyarpanahi
Merge branch 'release/600-release-candidate' into SPARKNLP-1077-Imple…
39ed5e7 
…menting-new-Qwen2-VL-models
@maziyarpanahi
Merge pull request #14474 from JohnSnowLabs/SPARKNLP-1077-Implementin…
c31306f 
…g-new-Qwen2-VL-models

SparkNLP 1077- Introducing Qwen2 - VL
@ahmedlone127
updating python and scala model names (#14488)
5417d91
@maziyarpanahi
Merge pull request #14489 from JohnSnowLabs/feature/SPARKNLP-1102-Add…
b35c90c 
…ing-support-to-read-Excel-files

[SPARKNLP-1102] Adding support to read Excel files
@maziyarpanahi
Merge pull request #14491 from JohnSnowLabs/feature/SPARKNLP-1103-Add…
e7a79fb 
…ing-support-to-read-PowerPoint-files

[SPARKNLP-1103] Adding support to read power point files
@maziyarpanahi
Merge pull request #14492 from JohnSnowLabs/feature/SPARKNLP-1105-Imp…
dd57c97 
…lement-ForMultipleChoice-for-ALBERT

[SPARKNLP-1105] Introducing AlbertForMultipleChoice Transformer
@maziyarpanahi
Merge branch 'release/600-release-candidate' into feature/SPARKNLP-11…
d7e2851 
…06-Implement-ForMultipleChoice-for-DistilBERT
@maziyarpanahi
Merge pull request #14493 from JohnSnowLabs/feature/SPARKNLP-1106-Imp…
cbbca68 
…lement-ForMultipleChoice-for-DistilBERT

[SPARKNLP-1106] Introducing DistilBertForMultipleChoice Transformer
@maziyarpanahi
Merge branch 'release/600-release-candidate' into feature/SPARKNLP-11…
06ef557 
…07-Implement-ForMultipeChoice-for-RoBERTa
@maziyarpanahi
Merge pull request #14495 from JohnSnowLabs/feature/SPARKNLP-1107-Imp…
7bd3ca0 
…lement-ForMultipeChoice-for-RoBERTa

[SPARKNLP-1107] Introducing RoBertaForMultipleChoice
@maziyarpanahi
Merge branch 'release/600-release-candidate' into feature/SPARKNLP-11…
c737a27 
…08-Implement-ForMultipleChoice-for-XLMRoBERTa
@maziyarpanahi
Merge pull request #14497 from JohnSnowLabs/feature/SPARKNLP-1108-Imp…
0420d04 
…lement-ForMultipleChoice-for-XLMRoBERTa

[SPARKNLP-1108] Introducing XlmRoBertaForMultipleChoice Transformer
@maziyarpanahi
Merge branch 'release/600-release-candidate' into feature/SPARKNLP-10…
2b363e2 
…98-Adding-a-PDF-Reader-to-Spark-NLP
@maziyarpanahi
Merge pull request #14499 from JohnSnowLabs/feature/SPARKNLP-1098-Add…
3999409 
…ing-a-PDF-Reader-to-Spark-NLP

[SPARKNLP-1098] Adding PDF reader support
@maziyarpanahi
Merge branch 'release/600-release-candidate' into SPARKNLP-1078-Imple…
7673843 
…ment-Llama-3.2-Vision-models
@maziyarpanahi
Merge pull request #14502 from JohnSnowLabs/SPARKNLP-1078-Implement-L…
6283a8f 
…lama-3.2-Vision-models

Sparknlp 1078 Introducing llama 3.2 vision models
@maziyarpanahi
Merge branch 'release/600-release-candidate' into feature/SPARKNLP-10…
6194f03 
…79-AutoGGUFVisionModel
@maziyarpanahi
Merge pull request #14505 from DevinTDHa/feature/SPARKNLP-1079-AutoGG…
3def1a0 
…UFVisionModel

[SPARKNLP-1079] AutoGGUFVisionModel
@maziyarpanahi
Merge pull request #14510 from JohnSnowLabs/Fixing-MXBAI-Embedding-no…
e4f1961 
…tebook

fixing typo in MXBAI notebook
@danilojsl
SPARKNLP-1109 Adding Extractor to Sparknlp (#14519)
a9d7980 
* [SPARKNLP-1109] Adding Extractor annotator

* [SPARKNLP-1109] Adding Cleaner annotator

* [SPARKNLP-1109] Adding missing index parameter in python

* [SPARKNLP-1109] Adding right inheritance for Cleaner in python

* [SPARKNLP-1109] Adding notebooks demo for Cleaner and Extractor

* [SPARKNLP-1110] Adding notebook demo for Email reader and Cleaner
@maziyarpanahi
Merge pull request #14524 from JohnSnowLabs/feature/SPARKNLP-1113-Add…
94290cc 
…ing-support-to-enhance-read-TXT-files

[SPARKNLP-1113] Adding Text Reader
@maziyarpanahi
Merge branch 'release/600-release-candidate' into SPARKNLP-1088-Imple…
d807b49 
…ment-DeepSeek-any-to-any-model
DevinTDHa and others added 30 commits October 22, 2025 14:39
@DevinTDHa
Bump Version [run doc]
b6a75ff
@actions-user @DevinTDHa
Update Scala and Python APIs
91a92e2
@DevinTDHa
restore Gemfile
17ad91c
@DevinTDHa
Restore previous doc dependencies
3bdb5af
@danilojsl @DevinTDHa
Fix google colab link on Readers Notebooks
fe1fb82
@danilojsl @DevinTDHa
[SPARKNLP-1306] Adding hierarchical support for PDF, MS Word and Mark…
554735a 
…down readers
@AbdullahMubeenAnwar @DevinTDHa
Add Java installation to Colab setup script
3b9acda 
The script now checks for Java and installs OpenJDK 11 if not present. JAVA_HOME and PATH are also set to ensure Java is available for subsequent steps.
@DevinTDHa
[SPARKNLP-1297] Improve performance of prepareBatchWordEmbeddings
4ea91e0 
- Fill output array in place to reduce RAM usage
@DevinTDHa
[SPARKNLP-1297] Improve DatasetHelper.randomize implementation
26e263f 
- use sortWithinPartitions instead of a custom map over partitions to
  not materialize rows
@DevinTDHa
[SPARKNLP-1297] NerDLGraphChecker fills label column metadata for gra…
5693c4f 
…ph params
@DevinTDHa
[SPARKNLP-1297] NerDLApproach skips dataset params extraction if NerD…
b1ce981 
…LGraphChecker added metadata to dataframe
@DevinTDHa
[SPARKNLP-1297] NerDLGraphChecker model fills metadata python side
cc37df2
@DevinTDHa
[SPARKNLP-1297] Cache by default to reduce processing
a02eb5e
@DevinTDHa
[SPARKNLP-1297] Use ArrayBuffer for batch creation
afa2c20
@DevinTDHa
[SPARKNLP-1297] NerDLGraphChecker: Fix tests for pyspark 3.3
916253d
@DevinTDHa
[SPARKNLP-1297] AutoGGUF python tests fix warning
70b80fd
@DevinTDHa
[SPARKNLP-1297] NerDL+GraphChecker: Move dataset length computation t…
2390a18 
…o checker model
@DevinTDHa
Update NerDL documentation
8537c95
@DevinTDHa
XML Reader and Reader2Doc Improvements (#14691)
3479083 
* Reader2Doc new defaults to always output single document

* XMLReader improvements

- doesn't output empty text anymore
- Can extract tag attribute values

* Reader2Doc improvements

- adjusted defaults, so we always output a single large document
- can specify join char with new parameter
- adjusted other readers for new defaults

* Reader2Doc improvements python side

* ReaderAssembler: Fix failing test
@DevinTDHa
Bump Version [run doc]
ad2ee11
@actions-user @DevinTDHa
Update Scala and Python APIs
6600098
@ahmedlone127 @DevinTDHa
[SPARKNLP-1309] Fix repeating tokens in WordEmbeddings
de9ef32
@DevinTDHa
NerDL: Improve calculation of dataset count
951331c
@DevinTDHa
Fix ReaderAssemblerTest PDF test failing
116d2a5
@DevinTDHa
Bump Version
da7a6ce
@DevinTDHa @ahmedlone127
@jsl-models @prabod @AbdullahMubeenAnwar
Merge Models Hub (#14697)
5a43dfc 
* Add model 2025-04-09-sent_arabic_monomodel_monotok_en

* Add model 2025-04-09-sent_schwurpert_pipeline_de

* Add model 2025-04-08-wav2vec2_large_xls_r_300m_hindi_devendr_en

* Add model 2025-04-08-dialogpt_medium_harry_pipeline_en

* Add model 2025-04-09-gpt_2_finetuning_airaid_en

* Add model 2025-04-08-mchammer_pipeline_en

* Add model 2025-04-09-wav2vec2_large_xls_r_300m_kor_11385_2_en

* Add model 2025-04-09-sent_bert_base_stackoverflow_comments_2m_pipeline_en

* Add model 2025-04-08-shape_nato_pipeline_en

* Add model 2025-04-09-burmese_awesome_wnut_model_ai_pipeline_en

* Add model 2025-04-09-vit_female_age_classification_en

* Add model 2025-04-09-vit_base_oxford_iiit_pets_niko132_pipeline_en

* Add model 2025-04-09-koriposting_en

* Add model 2025-04-09-rockdrigoma_pipeline_en

* Add model 2025-04-09-vit_base_patch16_224_finetuned_cedar_en

* Add model 2025-04-09-williamblakebot_pipeline_en

* Add model 2025-04-09-bert_base_train_book_ent_15p_ra_en

* Add model 2025-04-09-tinybert_train_book_ent_15p_en

* Add model 2025-04-08-exp_w2v2t_indonesian_xlsr_53_s358_id

* Add model 2025-04-08-bert_finetuned_ner_accelerate_atichets_pipeline_en

* Add model 2025-04-09-brad_buchsbaum_en

* Add model 2025-04-09-honeytech_pipeline_en

* Add model 2025-04-09-extended_gender_classifier_en

* Add model 2025-04-09-smids_1x_deit_tiny_rms_001_fold3_pipeline_en

* Add model 2025-04-09-icelynjennings_pipeline_en

* Add model 2025-04-09-jackposobiec_pipeline_en

* Add model 2025-04-09-sent_finnish_monomodel_monotok_pipeline_en

* Add model 2025-04-08-exp5_10partition_modelo_asl6000_pipeline_en

* Add model 2025-04-08-output_pipeline_pt

* Add model 2025-04-09-bert_finetuned_ner_huizhoucheng_en

* Add model 2025-04-09-icelynjennings_en

* Add model 2025-04-09-sent_tiny_mlm_glue_mnli_from_scratch_custom_tokenizer_expand_vocab_en

* Add model 2025-04-09-sent_drclips_en

* Add model 2025-04-09-sent_nbme_bio_clinicalbert_en

* Add model 2025-04-09-finetune_model_bert_en

* Add model 2025-04-09-bert_finetuned_ner_fundrais123_en

* Add model 2025-04-09-filler_username_pipeline_en

* Add model 2025-04-09-gpt2_chatbot_kuttersn_en

* Add model 2025-04-09-musebiihi_pipeline_en

* Add model 2025-04-09-disconcision_pipeline_en

* Add model 2025-04-09-arxiv_classifier_debertav3_en

* Add model 2025-04-08-wenger_en

* Add model 2025-04-08-burmese_awesome_model_recod_en

* Add model 2025-04-09-exp_w2v2t_portuguese_norwegian_pretraining_s84_pt

* Add model 2025-04-09-sent_bert_base_uncased_finetuned_mol_mlm_0_3_en

* Add model 2025-04-09-sent_tlm_rct_20k_large_scale_pipeline_en

* Add model 2025-04-08-jen_122_pipeline_en

* Add model 2025-04-09-dkulchar_pipeline_en

* Add model 2025-04-09-pico8degalaleo_pipeline_en

* Add model 2025-04-09-dialogpt_medium_captainprice_extended_en

* Add model 2025-04-09-wav2vec2_gujarati_stt_pipeline_en

* Add model 2025-04-08-smids_5x_deit_small_rms_00001_fold1_en

* Add model 2025-04-09-sent_minilm_l12_h384_uncased_finetuned_imdb_en

* Add model 2025-04-09-bert_suicide_detection_hk_large_nepal_bhasa_pipeline_en

* Add model 2025-04-09-distilbert_base_uncased_news_sentiment_finetuned_english_en

* Add model 2025-04-08-monopolyfornite_en

* Add model 2025-04-08-dialogpt_small_shy_en

* Add model 2025-04-09-distilbert_token_itr0_0_0001_editorials_01_03_2022_15_20_12_pipeline_en

* Add model 2025-04-09-kehlani_pipeline_en

* Add model 2025-04-09-burmese_awesome_humanaction_model_pipeline_en

* Add model 2025-04-09-tigers_side_vit_en

* Add model 2025-04-09-stp_classifier_13_1_en

* Add model 2025-04-08-nepali_grammar_error_detection_20250311_1323_en

* Add model 2025-04-09-mldz4shad_en

* Add model 2025-04-09-exp_w2v2t_swedish_northern_sami_xlsr_53_s328_en

* Add model 2025-04-09-bert_base_uncased_token_itr0_0_0001_train_essays_test_test_set_05_03_2022_05_58_31_en

* Add model 2025-04-09-wav2vec2_xlsr_53_marathi_large_en

* Add model 2025-04-09-hushem_5x_deit_small_adamax_0001_fold1_pipeline_en

* Add model 2025-04-09-lora_toxic_comment_pipeline_en

* Add model 2025-04-09-absa_turkish_bert_based_small_tr

* Add model 2025-04-08-smids_1x_deit_tiny_rms_001_fold5_en

* Add model 2025-04-09-wav2vec2_base_timit_demo_colab_bsen_pipeline_en

* Add model 2025-04-09-bert_base_turkish_sentiment_analysis_pipeline_tr

* Add model 2025-04-09-bert_base_turkish_sentiment_analysis_tr

* Add model 2025-04-09-bert_base_turkish_offensive_pipeline_tr

* Add model 2025-04-09-document_type_identification_en

* Add model 2025-04-09-sent_bnbert_pipeline_en

* Add model 2025-04-09-wav2vec2_large_xls_r_300m_tamil_colab_aakhilesh_en

* Add model 2025-04-08-sent_mbert_tlm_sent_english_chinese_en

* Add model 2025-04-08-pii_protection_model_pipeline_en

* Add model 2025-04-09-bert_tiny_finetuned_xglue_ner_en

* Add model 2025-04-08-wav2vec2_large_xls_r_300m_urdu_colab_pipeline_en

* Add model 2025-04-09-sent_bert_base_uncased_issues_128_xxr_pipeline_en

* Add model 2025-04-09-sent_mbert_tlm_chat_english_german_en

* Add model 2025-04-09-db_slr_1_1e_en

* Add model 2025-04-08-cher_pipeline_en

* Add model 2025-04-09-wav2vec2_base_libir_zenodo_pipeline_en

* Add model 2025-04-09-vit_epochs5_batch32_lr5e_05_size224_tiles4_seed3_q3_dropout_v2_en

* Add model 2025-04-09-wav2vec2_base_test_pipeline_en

* Add model 2025-04-09-lesseyecontact_en

* Add model 2025-04-09-wav2vec2_base_swbd_turn_eos_long_short_utt_removed_5percent_pipeline_en

* Add model 2025-04-09-micbucci_pipeline_en

* Add model 2025-04-09-veganseltzer_pipeline_en

* Add model 2025-04-08-dialogpt_medium_ff7_en

* Add model 2025-04-09-sent_storieslm_v1_1945_pipeline_en

* Add model 2025-04-09-sent_mbert_tlm_chat_english_chinese_pipeline_en

* Add model 2025-04-09-dialogpt_medium_milo_en

* Add model 2025-04-09-dataandme_en

* Add model 2025-04-09-lumetroid_en

* Add model 2025-04-09-dialogpt_medium_milo_pipeline_en

* Add model 2025-04-09-bbcqos_fitslut63_kellyg_official_en

* Add model 2025-04-09-stp_classifier_13_1_pipeline_en

* Add model 2025-04-09-vit_base_beans_demo_v5_hwooo92_pipeline_en

* Add model 2025-04-09-ridiculouscrabs_en

* Add model 2025-04-08-autotrain_20_12_2022_exam_part3_2543877946_pipeline_en

* Add model 2025-04-09-zemfira_en

* Add model 2025-04-09-michaeltrazzi_pipeline_en

* Add model 2025-04-09-absa_turkish_bert_based_small_pipeline_tr

* Add model 2025-04-09-gunna_pipeline_en

* Add model 2025-04-09-ourqueeningreen_pipeline_en

* Add model 2025-04-09-jenslennartsson_pipeline_en

* Add model 2025-04-09-sent_bottleneckbertsmall_en

* Add model 2025-04-09-dialogpt_mid_hpai_en

* Add model 2025-04-09-shelbythanna_en

* Add model 2025-04-09-macintoxic_en

* Add model 2025-04-09-square_rundi_square_rundi_second_vote_full_pic_25_age_gender_en

* Add model 2025-04-09-sent_first_try_rubert_200_16_16_25ep_en

* Add model 2025-04-09-postpostpostr_en

* Add model 2025-04-09-richardsocher_en

* Add model 2025-04-09-bert_base_german_cased_finetuned_subj_v1_pipeline_en

* Add model 2025-04-09-guggersylvain_pipeline_en

* Add model 2025-04-09-guggersylvain_en

* Add model 2025-04-09-macegrunow_en

* Add model 2025-04-09-macegrunow_pipeline_en

* Add model 2025-04-09-nueclear333_pipeline_en

* Add model 2025-04-09-olikuchi_en

* Add model 2025-04-09-wav2vec2_large_xlsr_53_full_train_full_train_pipeline_en

* Add model 2025-04-09-lanalilligant_en

* Add model 2025-04-08-peppa_pipeline_en

* Add model 2025-04-08-3_epochs_classifier_en

* Add model 2025-04-08-bert_base_greek_uncased_v1_finetuned_ner_pipeline_en

* Add model 2025-04-09-deit_base_patch16_224_rice_leaf_disease_augmented_tagalog_pipeline_en

* Add model 2025-04-08-wav2vec2_large_xlsr_estonian_m3hrdadfi_pipeline_et

* Add model 2025-04-08-sent_bert_base_uncased_multi_128_pipeline_en

* Add model 2025-04-09-mspunks_en

* Add model 2025-04-09-mspunks_pipeline_en

* Add model 2025-04-09-vit_base_patch16_224_masaratti_pipeline_en

* Add model 2025-04-09-burmese_awesome_emotion_identifier_model_en

* Add model 2025-04-09-wav2vec2_large_xls_r_300m_chichewa_colab_en

* Add model 2025-04-09-lesseyecontact_pipeline_en

* Add model 2025-04-07-dialogpt_small_rick_havokx_pipeline_en

* Add model 2025-04-08-wav2vec2_large_uralic_voxpopuli_v2_sami_parl_ext_ft_en

* Add model 2025-04-09-dnlklr_pipeline_en

* Add model 2025-04-09-wav2vec2_base_cynthia_timit_pipeline_en

* Add model 2025-04-09-mri_classifier_djibri_pipeline_en

* 2025-04-11-smolvlm_instruct_int4_en (#14550)

* Add model 2025-04-11-smolvlm_instruct_int4_en

* Add model 2025-04-14-paligemma_3b_pt_224_int4_en

* Add model 2025-04-15-paligemma_3b_ft_vqav2_448_int4_en

* Add model 2025-04-15-paligemma_3b_pt_224_int4_en

* Add model 2025-04-15-paligemma2_3b_pt_448_int4_en

* Add model 2025-04-15-paligemma2_3b_mix_224_int4_en

* Add model 2025-04-28-gemma_3_4b_it_int4_en

* Add model 2025-04-28-gemma_3_4b_pt_int4_en

---------

Co-authored-by: prabod <[email protected]>

* 2025-05-16-internvl2_1b_int4_en (#14577)

* Add model 2025-05-16-internvl2_1b_int4_en

* Add model 2025-05-16-internvl2_5_1b_int4_en

* Add model 2025-05-16-internvl3_1b_int4_en

* Add model 2025-05-16-internvl3_2b_int4_en

* Add model 2025-05-16-internvl3_8b_int4_en

* Add model 2025-05-16-internvl2_5_4b_int4_en

* Add model 2025-05-27-florence_2_base_ft_int4_en

* Add model 2025-05-27-florence_2_base_int4_en

* Add model 2025-05-27-florence_2_large_ft_int4_en

* Add model 2025-05-27-florence_2_large_int4_en

---------

Co-authored-by: prabod <[email protected]>

* 2025-05-17-internvl3_8b_int4_en (#14580)

* Add model 2025-05-17-internvl3_8b_int4_en

* Add model 2025-05-20-mmarco_mminilmv2_l12_h384_v1_nreimers_en

* Add model 2025-05-20-mmarco_mminilmv2_l12_h384_v1_nreimers_pipeline_en

* Add model 2025-05-20-bge_reranker_base_baai_en

* Add model 2025-05-20-xlm_roberta_base_language_detection_xx

* Add model 2025-05-20-bge_reranker_base_baai_pipeline_en

* Add model 2025-05-20-xlm_roberta_base_language_detection_pipeline_xx

* Add model 2025-05-20-twitter_xlm_roberta_base_sentiment_multilingual_xx

* Add model 2025-05-20-korean_reranker_ko

* Add model 2025-05-20-korean_reranker_pipeline_ko

* Add model 2025-05-20-twitter_xlm_roberta_base_sentiment_multilingual_pipeline_xx

* Add model 2025-05-20-bce_reranker_base_v1_maidalun1020_pipeline_en

* Add model 2025-05-20-bce_reranker_base_v1_maidalun1020_en

* Add model 2025-05-20-multilingual_iptc_news_topic_classifier_xx

* Add model 2025-05-20-bge_reranker_v2_m3_en

* Add model 2025-05-20-multilingual_iptc_news_topic_classifier_pipeline_xx

* Add model 2025-05-20-bge_reranker_v2_m3_pipeline_en

* Add model 2025-05-20-xlm_roberta_base_romanian_ner_ronec_ro

* Add model 2025-05-20-xlm_roberta_ner_japanese_ja

* Add model 2025-05-20-xlm_roberta_base_romanian_ner_ronec_pipeline_ro

* Add model 2025-05-20-xlm_roberta_ner_japanese_pipeline_ja

* Add model 2025-05-20-xlm_roberta_large_finetuned_conll03_english_xx

* Add model 2025-05-20-xlm_roberta_large_finetuned_conll03_german_xx

* Add model 2025-05-20-fullstop_punctuation_multilang_large_en

* Add model 2025-05-20-xlm_roberta_large_finetuned_conll03_english_pipeline_xx

* Add model 2025-05-20-fullstop_punctuation_multilang_large_pipeline_en

* Add model 2025-05-20-xlm_roberta_large_finetuned_conll03_german_pipeline_xx

* Add model 2025-05-20-xlm_roberta_large_ner_spanish_es

* Add model 2025-05-20-sent_twitter_xlm_roberta_base_en

* Add model 2025-05-20-sent_twitter_xlm_roberta_base_pipeline_en

* Add model 2025-05-20-sent_infoxlm_base_en

* Add model 2025-05-20-sent_mminilmv2_l12_h384_distilled_from_xlmr_large_en

* Add model 2025-05-20-sent_infoxlm_base_pipeline_en

* Add model 2025-05-20-sent_mminilmv2_l12_h384_distilled_from_xlmr_large_pipeline_en

* Add model 2025-05-20-sent_infoxlm_large_en

* Add model 2025-05-20-sent_xlm_roberta_large_xx

* Add model 2025-05-21-clip_vit_base_patch16_en

* Add model 2025-05-21-fashion_clip_en

* Add model 2025-05-21-clip_vit_base_patch16_pipeline_en

* Add model 2025-05-21-fashion_clip_pipeline_en

* Add model 2025-05-21-zero_shot_classifier_clip_vit_base_patch32_en

* Add model 2025-05-21-zero_shot_classifier_clip_vit_base_patch32_pipeline_en

* Add model 2025-05-21-clip_vit_large_patch14_336_en

* Add model 2025-05-21-xlmroberta_qa_ukrainian_uk

* Add model 2025-05-21-xlmroberta_qa_ukrainian_pipeline_uk

* Add model 2025-05-21-xlm_roberta_qa_xlm_roberta_base_arabic_ar

* Add model 2025-05-21-xlm_roberta_qa_xlm_roberta_base_arabic_pipeline_ar

* Add model 2025-05-21-xlm_roberta_qa_xlm_roberta_base_squad2_distilled_en

* Add model 2025-05-21-xlm_roberta_qa_xlm_roberta_base_squad2_distilled_pipeline_en

* Add model 2025-05-21-xlmr_large_qa_persian_farsi_fa

* Add model 2025-05-21-persian_xlm_roberta_large_en

* Add model 2025-05-21-xlmr_large_qa_persian_farsi_pipeline_fa

* Add model 2025-05-21-persian_xlm_roberta_large_pipeline_en

* Add model 2025-05-21-xlm_roberta_large_qa_multilingual_finedtuned_russian_xx

* Add model 2025-05-21-xlm_roberta_large_qa_multilingual_finedtuned_russian_pipeline_xx

* Add model 2025-05-21-xlm_roberta_large_xquad_en

* Add model 2025-05-21-xlm_roberta_large_xquad_pipeline_en

* Add model 2025-05-21-mminilmv2_l12_h384_distilled_from_xlmr_large_en

* Add model 2025-05-21-mminilmv2_l12_h384_distilled_from_xlmr_large_pipeline_en

* Add model 2025-05-21-twitter_xlm_roberta_base_en

* Add model 2025-05-21-twitter_xlm_roberta_base_pipeline_en

* Add model 2025-05-21-xlm_roberta_base_xx

* Add model 2025-05-21-xlm_roberta_base_pipeline_xx

* Add model 2025-05-21-infoxlm_large_en

* Add model 2025-05-21-infoxlm_base_en

* Add model 2025-05-21-infoxlm_base_pipeline_en

* Add model 2025-05-21-xlm_roberta_large_xx

* Add model 2025-05-21-xlm_v_base_xx

* Add model 2025-05-21-infoxlm_large_pipeline_en

* Add model 2025-05-21-xlm_roberta_large_pipeline_xx

* Add model 2025-05-21-xlm_v_base_pipeline_xx

* Add model 2025-05-21-robbert_v2_dutch_ner_nl

* Add model 2025-05-21-roberta_large_ner_english_en

* Add model 2025-05-21-robbert_v2_dutch_ner_pipeline_nl

* Add model 2025-05-21-roberta_large_tweetner7_all_en

* Add model 2025-05-21-roberta_large_ner_english_pipeline_en

* Add model 2025-05-21-roberta_token_classifier_sayula_popoluca_tagger_id

* Add model 2025-05-21-roberta_token_classifier_sayula_popoluca_tagger_pipeline_id

* Add model 2025-05-21-roberta_large_tweetner7_all_pipeline_en

* Add model 2025-05-22-twitter_roberta_base_sentiment_en

* Add model 2025-05-22-roberta_hate_speech_dynabench_r4_target_en

* Add model 2025-05-22-twitter_roberta_base_sentiment_latest_en

* Add model 2025-05-22-robertuito_sentiment_analysis_pipeline_es

* Add model 2025-05-22-roberta_base_go_emotions_en

* Add model 2025-05-22-roberta_hate_speech_dynabench_r4_target_pipeline_en

* Add model 2025-05-22-roberta_classifier_emotion_english_distil_base_pipeline_en

* Add model 2025-05-22-robertuito_sentiment_analysis_es

* Add model 2025-05-22-twitter_roberta_base_sentiment_latest_pipeline_en

* Add model 2025-05-22-twitter_roberta_base_sentiment_pipeline_en

* Add model 2025-05-22-roberta_classifier_emotion_english_distil_base_en

* Add model 2025-05-22-roberta_large_mnli_pipeline_en

* Add model 2025-05-22-roberta_large_mnli_en

* Add model 2025-05-22-roberta_base_go_emotions_pipeline_en

* Add model 2025-05-22-twitter_roberta_base_sentiment_latest_en

* Add model 2025-05-22-roberta_hate_speech_dynabench_r4_target_en

* Add model 2025-05-22-twitter_roberta_base_sentiment_en

* Add model 2025-05-22-robertuito_sentiment_analysis_pipeline_es

* Add model 2025-05-22-twitter_roberta_base_sentiment_pipeline_en

* Add model 2025-05-22-roberta_base_go_emotions_pipeline_en

* Add model 2025-05-22-roberta_hate_speech_dynabench_r4_target_pipeline_en

* Add model 2025-05-22-roberta_classifier_emotion_english_distil_base_en

* Add model 2025-05-22-robertuito_sentiment_analysis_es

* Add model 2025-05-22-roberta_large_mnli_en

* Add model 2025-05-22-roberta_large_mnli_pipeline_en

* Add model 2025-05-22-roberta_classifier_emotion_english_distil_base_pipeline_en

* Add model 2025-05-22-roberta_base_go_emotions_en

* Add model 2025-05-22-twitter_roberta_base_sentiment_latest_pipeline_en

* Add model 2025-05-22-distilroberta_base_en

* Add model 2025-05-22-codebert_python_en

* Add model 2025-05-22-distilroberta_base_pipeline_en

* Add model 2025-05-22-roberta_base_en

* Add model 2025-05-22-chemberta_zinc_base_v1_en

* Add model 2025-05-22-roberta_base_pipeline_en

* Add model 2025-05-22-roberta_large_en

* Add model 2025-05-22-chemberta_zinc_base_v1_pipeline_en

* Add model 2025-05-22-codebert_python_pipeline_en

* Add model 2025-05-22-roberta_large_pipeline_en

* Add model 2025-05-22-amd_power_dialer_v1_en

* Add model 2025-05-22-coherence_all_mpnet_base_v2_en

* Add model 2025-05-22-information_content_model_en

* Add model 2025-05-22-icelandic_nepal_bhasa_dataset_teacher_model_en

* Add model 2025-05-22-amd_full_phonetree_v1_pipeline_en

* Add model 2025-05-22-amd_partial_phonetree_v1_en

* Add model 2025-05-22-amd_partial_v1_en

* Add model 2025-05-22-burmese_setfit_classifier_threat_en

* Add model 2025-05-22-coherence_all_mpnet_base_v2_pipeline_en

* Add model 2025-05-22-hub_report_20241202125641_pipeline_en

* Add model 2025-05-22-amd_partial_v1_pipeline_en

* Add model 2025-05-22-amd_partial_phonetree_v1_pipeline_en

* Add model 2025-05-22-burmese_setfit_classifier_threat_pipeline_en

* Add model 2025-05-22-setfit_model_en

* Add model 2025-05-22-icelandic_nepal_bhasa_dataset_teacher_model_pipeline_en

* Add model 2025-05-22-setfit_model_pipeline_en

* Add model 2025-05-22-amd_power_dialer_v1_pipeline_en

* Add model 2025-05-22-hub_report_20241202125641_en

* Add model 2025-05-22-amd_full_phonetree_v1_en

* Add model 2025-05-22-information_content_model_pipeline_en

* Add model 2025-05-22-autotrain_kjxi3_hql8x_en

* Add model 2025-05-22-multi_qa_mpnet_base_dot_v1_finetuned_squad2_all_en

* Add model 2025-05-22-covid_qa_mpnet_en

* Add model 2025-05-22-multi_qa_mpnet_base_dot_v1_finetuned_squad2_all_pipeline_en

* Add model 2025-05-22-covid_qa_mpnet_pipeline_en

* Add model 2025-05-22-autotrain_kjxi3_hql8x_pipeline_en

* Add model 2025-05-22-multi_qa_mpnet_base_cos_v1_sentence_transformers_en

* Add model 2025-05-22-multi_qa_mpnet_base_dot_v1_en

* Add model 2025-05-22-paraphrase_mpnet_base_v2_en

* Add model 2025-05-22-patentsberta_en

* Add model 2025-05-22-all_mpnet_base_v2_sentence_transformers_pipeline_en

* Add model 2025-05-22-multi_qa_mpnet_base_cos_v1_sentence_transformers_pipeline_en

* Add model 2025-05-22-patentsberta_pipeline_en

* Add model 2025-05-22-fin_mpnet_base_en

* Add model 2025-05-22-nli_mpnet_base_v2_en

* Add model 2025-05-22-fin_mpnet_base_pipeline_en

* Add model 2025-05-22-biolord_2023_c_en

* Add model 2025-05-22-all_mpnet_base_v2_sentence_transformers_en

* Add model 2025-05-22-paraphrase_mpnet_base_v2_pipeline_en

* Add model 2025-05-22-biolord_2023_pipeline_en

* Add model 2025-05-22-multi_qa_mpnet_base_dot_v1_pipeline_en

* Add model 2025-05-22-biolord_2023_c_pipeline_en

* Add model 2025-05-22-biolord_2023_en

* Add model 2025-05-22-nli_mpnet_base_v2_pipeline_en

* Add model 2025-05-22-e5_small_v2_intfloat_en

* Add model 2025-05-22-e5_small_en

* Add model 2025-05-22-e5_small_v2_intfloat_pipeline_en

* Add model 2025-05-22-e5_small_pipeline_en

* Add model 2025-05-22-e5_base_v2_intfloat_pipeline_en

* Add model 2025-05-22-e5_base_pipeline_en

* Add model 2025-05-22-sentence_transformers_e5_large_v2_en

* Add model 2025-05-22-e5_large_en

* Add model 2025-05-22-sentence_transformers_e5_large_v2_pipeline_en

* Add model 2025-05-22-e5_base_en

* Add model 2025-05-22-e5_base_v2_intfloat_en

* Add model 2025-05-22-e5_large_pipeline_en

* Add model 2025-05-22-e5_large_v2_intfloat_en

* Add model 2025-05-22-e5_large_v2_intfloat_pipeline_en

* Add model 2025-05-24-e5_small_en

* Add model 2025-05-24-e5_small_v2_intfloat_en

* Add model 2025-05-24-e5_small_pipeline_en

* Add model 2025-05-24-e5_base_v2_intfloat_pipeline_en

* Add model 2025-05-24-e5_small_v2_intfloat_pipeline_en

* Add model 2025-05-24-sentence_transformers_e5_large_v2_en

* Add model 2025-05-24-e5_base_v2_intfloat_en

* Add model 2025-05-24-e5_large_en

* Add model 2025-05-24-e5_base_pipeline_en

* Add model 2025-05-24-sentence_transformers_e5_large_v2_pipeline_en

* Add model 2025-05-24-e5_large_v2_intfloat_en

* Add model 2025-05-24-e5_large_pipeline_en

* Add model 2025-05-24-e5_base_en

* Add model 2025-05-25-distilbert_tok_classifier_typo_detector_en

* Add model 2025-05-25-biomedical_ner_all_d4data_en

* Add model 2025-05-25-distilbert_ner_distilbert_base_cased_finetuned_conll03_english_en

* Add model 2025-05-25-distilbert_ner_distilbert_base_cased_finetuned_conll03_english_pipeline_en

* Add model 2025-05-25-distilbert_finetuned_ai4privacy_v2_en

* Add model 2025-05-25-distilbert_ner_distilbert_base_multilingual_cased_ner_hrl_nl

* Add model 2025-05-25-biomedical_ner_all_d4data_pipeline_en

* Add model 2025-05-25-distilbert_base_multilingual_cased_pii_xx

* Add model 2025-05-25-distilbert_token_classifier_keyphrase_extraction_inspec_pipeline_en

* Add model 2025-05-25-chonky_distilbert_base_uncased_1_en

* Add model 2025-05-25-distilbert_ner_dslim_en

* Add model 2025-05-25-distilbert_tok_classifier_typo_detector_pipeline_en

* Add model 2025-05-25-chonky_distilbert_base_uncased_1_pipeline_en

* Add model 2025-05-25-distilbert_finetuned_ai4privacy_v2_pipeline_en

* Add model 2025-05-25-distilbert_base_multilingual_cased_pii_pipeline_xx

* Add model 2025-05-25-distilbert_ner_distilbert_base_multilingual_cased_ner_hrl_pipeline_nl

* Add model 2025-05-25-distilbert_ner_dslim_pipeline_en

* Add model 2025-05-25-distilbert_token_classifier_keyphrase_extraction_inspec_en

* Add model 2025-05-25-distilbert_base_uncased_go_emotions_student_en

* Add model 2025-05-25-toxic_comment_model_en

* Add model 2025-05-25-nsfw_text_classifier_en

* Add model 2025-05-25-distilbert_nsfw_text_classifier_pipeline_en

* Add model 2025-05-25-distilbert_base_uncased_go_emotions_student_pipeline_en

* Add model 2025-05-25-toxic_comment_model_pipeline_en

* Add model 2025-05-25-nsfw_text_classifier_pipeline_en

* Add model 2025-05-25-distilbert_nsfw_text_classifier_en

* Add model 2025-05-25-multilingual_sentiment_analysis_xx

* Add model 2025-05-25-multilingual_sentiment_analysis_pipeline_xx

* Add model 2025-05-27-thainer_corpus_v2_base_model_th

* Add model 2025-05-27-thainer_corpus_v2_base_model_pipeline_th

* Add model 2025-05-27-phayathaibert_thainer_th

* Add model 2025-05-27-nermembert_base_4entities_fr

* Add model 2025-05-27-cas_biomedical_sayula_popoluca_tagging_fr

* Add model 2025-05-27-phayathaibert_thainer_pipeline_th

* Add model 2025-05-27-nermembert_large_3entities_fr

* Add model 2025-05-27-nermembert_large_3entities_pipeline_fr

* Add model 2025-05-27-cas_biomedical_sayula_popoluca_tagging_pipeline_fr

* Add model 2025-05-27-nermembert_base_4entities_pipeline_fr

* Add model 2025-05-27-rubert_base_cased_nli_threeway_ru

* Add model 2025-05-27-rubert_base_cased_nli_threeway_pipeline_ru

---------

Co-authored-by: ahmedlone127 <[email protected]>

* Add model 2025-06-10-e5v_int4_en (#14599)

Co-authored-by: prabod <[email protected]>

* Add model 2025-06-23-minilm_l6_v2_en

* Add model 2025-06-22-bert_classifier_finbert_tone_en

* Add model 2025-06-22-bert_classifier_finbert_tone_pipeline_en

* Add model 2025-06-22-finbert_pipeline_en

* Add model 2025-06-22-bert_base_multilingual_uncased_sentiment_xx

* Add model 2025-06-22-bert_base_multilingual_uncased_sentiment_pipeline_xx

* Add model 2025-06-22-finbert_en

* Add model 2025-06-22-bert_base_multilingual_cased_google_bert_xx

* Add model 2025-06-22-bert_base_multilingual_cased_google_bert_pipeline_xx

* Add model 2025-06-22-bert_base_uncased_google_bert_en

* Add model 2025-06-22-bert_base_cased_google_bert_pipeline_en

* Add model 2025-06-22-bert_base_cased_google_bert_en

* Add model 2025-06-22-bert_base_uncased_google_bert_pipeline_en

* Add model 2025-06-22-sent_bert_base_multilingual_cased_xx

* Add model 2025-06-22-sent_bert_base_multilingual_cased_pipeline_xx

* Add model 2025-06-22-sent_bert_base_cased_en

* Add model 2025-06-22-sent_bert_base_cased_pipeline_en

* Add model 2025-06-22-sent_bert_base_uncased_pipeline_en

* Add model 2025-06-22-sent_bert_base_uncased_en

* Add model 2025-06-22-camembert_bio_base_fr

* Add model 2025-06-22-camembert_bio_base_pipeline_fr

* Add model 2025-06-22-drbert_7gb_fr

* Add model 2025-06-22-umberto_commoncrawl_cased_v1_it

* Add model 2025-06-22-camembert_base_fr

* Add model 2025-06-22-umberto_commoncrawl_cased_v1_pipeline_it

* Add model 2025-06-22-drbert_7gb_pipeline_fr

* Add model 2025-06-22-sloberta_pipeline_sl

* Add model 2025-06-22-camembert_base_pipeline_fr

* Add model 2025-06-22-sloberta_sl

* Add model 2025-06-22-wangchanberta_finetuned_sentiment_th

* Add model 2025-06-22-wangchanberta_finetuned_sentiment_pipeline_th

* Add model 2025-06-22-feel_italian_italian_emotion_it

* Add model 2025-06-22-feel_italian_italian_sentiment_it

* Add model 2025-06-22-finance_sentiment_french_base_fr

* Add model 2025-06-22-feel_italian_italian_emotion_pipeline_it

* Add model 2025-06-22-finance_sentiment_french_base_pipeline_fr

* Add model 2025-06-22-ag_nli_dets_sentence_similarity_v4_pipeline_xx

* Add model 2025-06-22-ag_nli_dets_sentence_similarity_v4_xx

* Add model 2025-06-22-feel_italian_italian_sentiment_pipeline_it

* Add model 2025-06-24-efficient_splade_vietnamese_bt_large_doc_en

* Add model 2025-06-24-distilbert_base_cased_en

* Add model 2025-06-24-distilbert_base_multilingual_cased_pipeline_xx

* Add model 2025-06-24-distilbert_base_german_cased_de

* Add model 2025-06-24-distilbert_base_cased_pipeline_en

* Add model 2025-06-24-distilbert_base_multilingual_cased_xx

* Add model 2025-06-24-distilbert_base_uncased_en

* Add model 2025-06-24-opensearch_neural_sparse_encoding_v2_distill_en

* Add model 2025-06-24-opensearch_neural_sparse_encoding_v2_distill_pipeline_en

* Add model 2025-06-24-distilbert_base_uncased_pipeline_en

* Add model 2025-06-24-efficient_splade_vietnamese_bt_large_doc_pipeline_en

* Add model 2025-06-24-clinicalbert_pipeline_en

* Add model 2025-06-24-opensearch_neural_sparse_encoding_doc_v2_distill_pipeline_en

* Add model 2025-06-24-opensearch_neural_sparse_encoding_doc_v2_distill_en

* Add model 2025-06-24-clinicalbert_en

* Add model 2025-06-24-distilbert_base_german_cased_pipeline_de

* Add model 2025-06-24-tiny_distilbert_base_cased_distilled_squad_en

* Add model 2025-06-24-tiny_distilbert_base_cased_distilled_squad_pipeline_en

* Add model 2025-06-24-distilbert_base_uncased_distilled_squad_distilbert_en

* Add model 2025-06-24-distilbert_base_uncased_distilled_squad_distilbert_pipeline_en

* Add model 2025-06-24-question_answering_v2_pipeline_en

* Add model 2025-06-24-distilbert_base_cased_distilled_squad_distilbert_en

* Add model 2025-06-24-distilbert_base_uncased_finetuned_squad_full_pipeline_en

* Add model 2025-06-24-distilbert_base_cased_distilled_squad_distilbert_pipeline_en

* Add model 2025-06-24-question_answering_v2_en

* Add model 2025-06-24-distilbert_base_uncased_finetuned_squad_full_en

* Add model 2025-06-24-hubert_large_japanese_asr_ja

* Add model 2025-06-24-hubert_large_arabic_egyptian_ar

* Add model 2025-06-24-hubert_large_japanese_asr_pipeline_ja

* Add model 2025-06-24-hubert_large_arabic_egyptian_pipeline_ar

* Add model 2025-06-24-distilbart_mnli_12_6_en

* Add model 2025-06-24-distilbart_mnli_12_3_en

* Add model 2025-06-24-distilbart_mnli_12_6_pipeline_en

* Add model 2025-06-24-distilbart_mnli_12_1_en

* Add model 2025-06-24-awesome_fb_model_en

* Add model 2025-06-24-distilbart_mnli_12_3_pipeline_en

* Add model 2025-06-24-distilbart_mnli_12_1_pipeline_en

* Add model 2025-06-24-distilbart_mnli_12_9_pipeline_en

* Add model 2025-06-24-bart_mnli_cnn_256_pipeline_en

* Add model 2025-06-24-distilbart_mnli_12_9_en

* Add model 2025-06-24-bart_mnli_cnn_256_en

* Add model 2025-06-24-awesome_fb_model_pipeline_en

* Add model 2025-06-24-bart_large_mnli_yahoo_answers_joeddav_pipeline_en

* Add model 2025-06-24-bart_large_mnli_yahoo_answers_joeddav_en

* Add model 2025-07-03-phi_3.5_mini_instruct_int4_en

* 2025-07-15-bge_medembed_base_v0_1_openvino_en (#14629)

* Add model 2025-07-15-bge_medembed_base_v0_1_openvino_en

* Add model 2025-07-15-bge_medembed_large_v0_1_openvino_en

* Add model 2025-07-15-all_mpnet_base_v2_openvino_en

* Update 2025-07-15-bge_medembed_base_v0_1_openvino_en.md

* Update 2025-07-15-bge_medembed_large_v0_1_openvino_en.md

* Add model 2025-07-18-nuextract_2.0_2B_en

---------

Co-authored-by: AbdullahMubeenAnwar <[email protected]>
Co-authored-by: Abdullah mubeen <[email protected]>

* 2025-07-25-phi_4_mini_instruct_q4_k_m_gguf_en (#14638)

* Add model 2025-07-25-phi_4_mini_instruct_q4_k_m_gguf_en

* Add model 2025-07-25-phi_4_mini_instruct_q8_0_gguf_en

* Add model 2025-07-25-phi_4_mini_instruct_bf16_gguf_en

* Add model 2025-07-25-Phi_4_mini_instruct_int4_openvino_en

* Update 2025-07-25-Phi_4_mini_instruct_int4_openvino_en.md

* Update 2025-07-25-Phi_4_mini_instruct_int4_openvino_en.md

* Add model 2025-07-25-phi_4_mini_instruct_int8_openvino_en

---------

Co-authored-by: AbdullahMubeenAnwar <[email protected]>
Co-authored-by: Abdullah mubeen <[email protected]>

* 2025-07-31-qwen3_4b_q4_k_m_gguf_en (#14639)

* Add model 2025-07-31-qwen3_4b_q4_k_m_gguf_en

* Add model 2025-07-31-qwen3_4b_q8_0_gguf_en

* Add model 2025-07-31-qwen3_4b_bf16_gguf_en

---------

Co-authored-by: AbdullahMubeenAnwar <[email protected]>

* 2025-08-04-Qwen3_Embedding_0.6B_Q8_0_gguf_en (#14642)

* Add model 2025-08-04-Qwen3_Embedding_0.6B_Q8_0_gguf_en

* Update 2025-08-04-Qwen3_Embedding_0.6B_Q8_0_gguf_en.md

* Add model 2025-08-04-Phi_4_mini_instruct_Q4_K_M_gguf_en

* Add model 2025-08-04-Qwen2.5_VL_3B_Instruct_Q4_K_M_gguf_en

---------

Co-authored-by: DevinTDHa <[email protected]>
Co-authored-by: Devin Ha <[email protected]>

* Add model 2025-08-11-qwen2_vl_2b_instruct_q4_gguf_en (#14648)

Co-authored-by: AbdullahMubeenAnwar <[email protected]>

* Add model 2025-09-01-bge_reranker_v2_m3_Q4_K_M_en

* Add model 2025-09-15-qwen2.5_vl_7b_instruct_q16_gguf_en (#14661)

Co-authored-by: AbdullahMubeenAnwar <[email protected]>

* 2025-11-03-umlsbert_eng_onnx_en (#14683)

* Add model 2025-11-03-umlsbert_eng_onnx_en

* Update 2025-11-03-umlsbert_eng_onnx_en.md

---------

Co-authored-by: AbdullahMubeenAnwar <[email protected]>
Co-authored-by: Abdullah mubeen <[email protected]>

* Add model 2025-11-04-bert_base_uncased_multiple_choice_en

* Add model 2025-11-07-distilbert_base_cased_en (#14688)

Co-authored-by: AbdullahMubeenAnwar <[email protected]>

* Add model 2025-11-07-bge_base_en_v1_5_onnx_en (#14690)

Co-authored-by: AbdullahMubeenAnwar <[email protected]>

* Add model 2025-11-09-glove2024_wikigiga_200d_en

---------

Co-authored-by: ahmedlone127 <[email protected]>
Co-authored-by: jsl-models <[email protected]>
Co-authored-by: prabod <[email protected]>
Co-authored-by: AbdullahMubeenAnwar <[email protected]>
Co-authored-by: Abdullah mubeen <[email protected]>
@ahmedlone127 @DevinTDHa
[SPARKNLP-1315] changing input data type for CamemBertForTokenClassif…
99fe94d 
…ic… (#14701)

* SPARKNLP-1315 changing input data type for CamemBertForTokenClassification from int 64 to 32

* SPARKNLP-1315 adding test for tensorflow models
@DevinTDHa
[SPARKNLP-1317] Further NerDL Optimizations (#14699)
dba4495 
* NerDLGraphChecker add missing setter on scala side

* Introduce NerDLDataLoader for NerDLApproach

Threaded NerDLDataLoader fetches batches in the background while
training is happening in NerDLApproach, reducing idle time in the driver
thread.

* NerDLApproach: Optimize partitioning flag

Allow NerDLApproach to repartition the input dataset, so the driver does
not go out of memory when training on large partitions.

* NerDL Optimizations python side
@DevinTDHa
Bump Version [run doc]
aa63267
@actions-user @DevinTDHa
Update Scala and Python APIs
34b1ab5
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.