Add BERTopic model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ctfidf_config.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,169 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# C2-Topic-Model-100
+
+This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model. 
+BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets. 
+
+## Usage 
+
+To use this model, please install BERTopic:
+
+```
+pip install -U bertopic
+```
+
+You can use the model as follows:
+
+```python
+from bertopic import BERTopic
+topic_model = BERTopic.load("AlexanderHolmes0/C2-Topic-Model-100")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 100
+* Number of training documents: 828299
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | you - to - your - and - that | 546 | -1_you_to_your_and | 
+| 0 | price - of - in - value - index | 34030 | 0_price_of_in_value | 
+| 1 | you - card - credit - your - to | 102457 | 1_you_card_credit_your | 
+| 2 | rating - trust - shares - quaer - stock | 171217 | 2_rating_trust_shares_quaer | 
+| 3 | game - washington - wizards - the - season | 30538 | 3_game_washington_wizards_the | 
+| 4 | app - easy - love - great - my | 57205 | 4_app_easy_love_great | 
+| 5 | and - to - the - in - about | 27829 | 5_and_to_the_in | 
+| 6 | deals - save - com - black - deal | 67826 | 6_deals_save_com_black | 
+| 7 | app - my - it - me - account | 23384 | 7_app_my_it_me | 
+| 8 | easy - use - very - convenient - navigate | 25012 | 8_easy_use_very_convenient | 
+| 9 | tickets - ticketmaster - swift - presale - taylor | 20637 | 9_tickets_ticketmaster_swift_presale | 
+| 10 | you - work - to - that - it | 14825 | 10_you_work_to_that | 
+| 11 | rating - stock - shares - 00 - quaer | 16734 | 11_rating_stock_shares_00 | 
+| 12 | patent - virginia - alexandria - inventors - assigned | 9483 | 12_patent_virginia_alexandria_inventors | 
+| 13 | de - la - en - el - que | 5562 | 13_de_la_en_el | 
+| 14 | it - you - wiki - that - he | 7589 | 14_it_you_wiki_that | 
+| 15 | biden - capitol - that - trump - the | 29399 | 15_biden_capitol_that_trump | 
+| 16 | great - good - excellent - awesome - very | 15650 | 16_great_good_excellent_awesome | 
+| 17 | hi - hey - me - hello - hu | 9391 | 17_hi_hey_me_hello | 
+| 18 | cou - county - case - to - the | 3496 | 18_cou_county_case_to | 
+| 19 | arena - center - tour - music - tickets | 9937 | 19_arena_center_tour_music | 
+| 20 | ihearadio - jingle - ball - photo - her | 16963 | 20_ihearadio_jingle_ball_photo | 
+| 21 | and - to - the - you - for | 7139 | 21_and_to_the_you | 
+| 22 | garcia - davis - fight - gervonta - he | 13708 | 22_garcia_davis_fight_gervonta | 
+| 23 | ihearadio - photo - festival - music - getty | 3245 | 23_ihearadio_photo_festival_music | 
+| 24 | farm - farmers - loans - loan - mogage | 4962 | 24_farm_farmers_loans_loan | 
+| 25 | banks - bank - zelle - overdraft - fees | 2692 | 25_banks_bank_zelle_overdraft | 
+| 26 | covid - nyc - bar - search - map | 8970 | 26_covid_nyc_bar_search | 
+| 27 | helix - solutions - aris - energy - water | 1398 | 27_helix_solutions_aris_energy | 
+| 28 | bs - blt - bue - crap - bib | 1635 | 28_bs_blt_bue_crap | 
+| 29 | matador - ironwood - resources - mtdr - company | 1286 | 29_matador_ironwood_resources_mtdr | 
+| 30 | doubleverify - dv - shopify - rating - stock | 1336 | 30_doubleverify_dv_shopify_rating | 
+| 31 | __ - http - add - me - please | 1184 | 31____http_add_me | 
+| 32 | amphastar - crowdstrike - pharmaceuticals - rating - stock | 1583 | 32_amphastar_crowdstrike_pharmaceuticals_rating | 
+| 33 | boy - wentz - band - fob - ego | 1087 | 33_boy_wentz_band_fob | 
+| 34 | nabors - industries - arvinas - rating - drilling | 1233 | 34_nabors_industries_arvinas_rating | 
+| 35 | arena - blink - center - may - 182 | 1215 | 35_arena_blink_center_may | 
+| 36 | biosciences - akoya - biopharmaceuticals - stock - of | 1573 | 36_biosciences_akoya_biopharmaceuticals_stock | 
+| 37 | therapeutics - rapt - chimerix - stock - rating | 1795 | 37_therapeutics_rapt_chimerix_stock | 
+| 38 | written - news - episode - video - the | 1170 | 38_written_news_episode_video | 
+| 39 | one - capital - you - it - that | 5740 | 39_one_capital_you_it | 
+| 40 | wizards - homebody - predictions - odds - picks | 13044 | 40_wizards_homebody_predictions_odds | 
+| 41 | sweepstakes - sponsor - any - prize - or | 2093 | 41_sweepstakes_sponsor_any_prize | 
+| 42 | cameron - her - getty - images - photo | 852 | 42_cameron_her_getty_images | 
+| 43 | arena - center - aug - drake - tour | 785 | 43_arena_center_aug_drake | 
+| 44 | eur1 - eur - of - price - in | 1120 | 44_eur1_eur_of_price | 
+| 45 | puth - like - love - he - song | 2216 | 45_puth_like_love_he | 
+| 46 | easy - very - peasy - fast - quick | 1798 | 46_easy_very_peasy_fast | 
+| 47 | immersive - vr - tech - forward - looking | 2191 | 47_immersive_vr_tech_forward | 
+| 48 | chargepoint - chpt - rating - stock - shares | 1611 | 48_chargepoint_chpt_rating_stock | 
+| 49 | chvrches - hott - stranding - her - mayberry | 592 | 49_chvrches_hott_stranding_her | 
+| 50 | tkk - tk - tzsarbreaux - 20se - ttds | 563 | 50_tkk_tk_tzsarbreaux_20se | 
+| 51 | morello - white - belasco - untamable - unpredictable | 630 | 51_morello_white_belasco_untamable | 
+| 52 | our - peapack - gladstone - we - and | 561 | 52_our_peapack_gladstone_we | 
+| 53 | white - footage - ihearadio - his - beck | 677 | 53_white_footage_ihearadio_his | 
+| 54 | libey - energy - lb - oilfield - stock | 668 | 54_libey_energy_lb_oilfield | 
+| 55 | trump - investigation - james - attorney - his | 853 | 55_trump_investigation_james_attorney | 
+| 56 | adr - adrs - mellon - of - in | 1024 | 56_adr_adrs_mellon_of | 
+| 57 | energy - rating - chesapeake - oil - research | 3156 | 57_energy_rating_chesapeake_oil | 
+| 58 | center - arena - 12 - tso - ghosts | 2762 | 58_center_arena_12_tso | 
+| 59 | socure - identity - verification - fraud - ventures | 484 | 59_socure_identity_verification_fraud | 
+| 60 | dua - her - pop - lipa - ihearadio | 567 | 60_dua_her_pop_lipa | 
+| 61 | laroi - kid - his - song - unreleased | 747 | 61_laroi_kid_his_song | 
+| 62 | fennec - pharmaceuticals - fenc - rating - stock | 413 | 62_fennec_pharmaceuticals_fenc_rating | 
+| 63 | lizzo - dance - kardashian - her - noh | 466 | 63_lizzo_dance_kardashian_her | 
+| 64 | saul - centers - bfs - rating - shares | 454 | 64_saul_centers_bfs_rating | 
+| 65 | ryan - brothers - jingle - ihearadio - ajr | 316 | 65_ryan_brothers_jingle_ihearadio | 
+| 66 | food - wine - festival - chef - beach | 536 | 66_food_wine_festival_chef | 
+| 67 | arena - spos - pumpkins - center - smashing | 1107 | 67_arena_spos_pumpkins_center | 
+| 68 | her - max - ava - jingle - ihearadio | 636 | 68_her_max_ava_jingle | 
+| 69 | montrose - environmental - meg - group - rating | 420 | 69_montrose_environmental_meg_group | 
+| 70 | lauv - song - his - photo - jingle | 347 | 70_lauv_song_his_photo | 
+| 71 | niall - harry - album - circus - direction | 344 | 71_niall_harry_album_circus | 
+| 72 | flute - lizzo - library - crystal - congress | 396 | 72_flute_lizzo_library_crystal | 
+| 73 | alamos - agi - gold - newswire - globe | 1246 | 73_alamos_agi_gold_newswire | 
+| 74 | capitals - sharks - nhl - expe - odds | 516 | 74_capitals_sharks_nhl_expe | 
+| 75 | 07 - 06 - center - arena - paramore | 571 | 75_07_06_center_arena | 
+| 76 | dcfc - tritium - chargers - rating - limited | 698 | 76_dcfc_tritium_chargers_rating | 
+| 77 | groove - engagement - sales - platform - salesforce | 288 | 77_groove_engagement_sales_platform | 
+| 78 | album - billboard - songs - cha - swift | 354 | 78_album_billboard_songs_cha | 
+| 79 | google - viual - card - you - your | 962 | 79_google_viual_card_you | 
+| 80 | train - album - am - gold - ihearadio | 1194 | 80_train_album_am_gold | 
+| 81 | ihearadio - chili - peppers - hair - he | 540 | 81_ihearadio_chili_peppers_hair | 
+| 82 | dj - baseball - ice - hockey - football | 381 | 82_dj_baseball_ice_hockey | 
+| 83 | dhabi - abu - adcb - aed1 - al | 749 | 83_dhabi_abu_adcb_aed1 | 
+| 84 | salle - la - saint - joseph - explorers | 360 | 84_salle_la_saint_joseph | 
+| 85 | holiday - day - open - closed - holidays | 254 | 85_holiday_day_open_closed | 
+| 86 | iheacountry - festival - country - ihearadio - austin | 976 | 86_iheacountry_festival_country_ihearadio | 
+| 87 | foods - simply - smpl - good - kilts | 1490 | 87_foods_simply_smpl_good | 
+| 88 | parking - http - howard - city - divisons | 387 | 88_parking_http_howard_city | 
+| 89 | bellamy - delonge - extraterrestrial - ego - alter | 373 | 89_bellamy_delonge_extraterrestrial_ego | 
+| 90 | rhett - his - country - thomas - album | 289 | 90_rhett_his_country_thomas | 
+| 91 | lgbt - prnewswire - national - nglcc - wbenc | 4136 | 91_lgbt_prnewswire_national_nglcc | 
+| 92 | tires - tire - goodyear - save - walma | 912 | 92_tires_tire_goodyear_save | 
+| 93 | customer - marketing - business - customers - your | 453 | 93_customer_marketing_business_customers | 
+| 94 | twitter - musk - that - to - elon | 844 | 94_twitter_musk_that_to | 
+| 95 | cincinnati - fhlb - results - unaudited - prnewswire | 1539 | 95_cincinnati_fhlb_results_unaudited | 
+| 96 | accurate - complete - securities - reader - necessarily | 581 | 96_accurate_complete_securities_reader | 
+| 97 | 22 - arena - center - vengeance - viva | 383 | 97_22_arena_center_vengeance | 
+| 98 | button - mobile - marketers - commerce - platform | 733 | 98_button_mobile_marketers_commerce |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: None
+* low_memory: False
+* min_topic_size: 500
+* n_gram_range: (1, 1)
+* nr_topics: 100
+* seed_topic_list: None
+* top_n_words: 10
+* verbose: True
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 1.26.4
+* HDBSCAN: 0.8.33
+* UMAP: 0.5.5
+* Pandas: 2.0.3
+* Scikit-Learn: 1.4.1.post1
+* Sentence-transformers: 2.5.1
+* Transformers: 4.39.1
+* Numba: 0.59.1
+* Plotly: 5.20.0
+* Python: 3.11.8

config.json

@@ -0,0 +1,17 @@
+{
+  "calculate_probabilities": false,
+  "language": null,
+  "low_memory": false,
+  "min_topic_size": 500,
+  "n_gram_range": [
+    1,
+    1
+  ],
+  "nr_topics": 100,
+  "seed_topic_list": null,
+  "top_n_words": 10,
+  "verbose": true,
+  "zeroshot_min_similarity": 0.7,
+  "zeroshot_topic_list": null,
+  "embedding_model": "BAAI/bge-small-en-v1.5"
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3297bdbc979e6a9e5d55a61ed8d2c91102c645a19ea4cd0ceb2fe5022103d0fd
+size 30316372

ctfidf_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b5e69423c304d4029578a1163d863099aed27168c855f27b4aa42f95e8489d
+size 20526034

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ec3aaa3567972184a4083f1a7688fb512a33b34a60193062178de3bd393fe2
+size 153688