Add BERTopic model

README.md

@@ -0,0 +1,203 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# bertopic_BREAK50
+
+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("tyrealqian/bertopic_BREAK50")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 134
+* Number of training documents: 52070
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | imagine imagine - imagine - golfer - playing - play | 26 | -1_imagine imagine_imagine_golfer_playing | 
+| 0 | brysondechambeau - user - efarley_jr - americaisbasedandepic - election | 26268 | 0_brysondechambeau_user_efarley_jr_americaisbasedandepic | 
+| 1 | biden - think biden - joe - joe biden - biden golf | 7535 | 1_biden_think biden_joe_joe biden | 
+| 2 | reeeeeeeeeee hot - trump gc - whatttttttttt - wow yes - gc yesssssss | 1291 | 2_reeeeeeeeeee hot_trump gc_whatttttttttt_wow yes | 
+| 3 | trump bryson - bryson trump - bryson president - thank bryson - job bryson | 749 | 3_trump bryson_bryson trump_bryson president_thank bryson | 
+| 4 | maga lol - yessssss - yessss - lfg - badass mwga | 698 | 4_maga lol_yessssss_yessss_lfg | 
+| 5 | awesome awesome - epic - awesome amazing - awesome absolutely - awesome | 577 | 5_awesome awesome_epic_awesome amazing_awesome absolutely | 
+| 6 | golf video - best golf - youtube golf - greatest golf - video time | 494 | 6_golf video_best golf_youtube golf_greatest golf | 
+| 7 | ear - filmed - attempt - assassination - assassination attempt | 491 | 7_ear_filmed_attempt_assassination | 
+| 8 | chill - trump chill - good trump - dude trump - stick | 488 | 8_chill_trump chill_good trump_dude trump | 
+| 9 | million - subs - million views - views - congrats | 475 | 9_million_subs_million views_views | 
+| 10 | cart - boxes - tee boxes - driving - tee box | 441 | 10_cart_boxes_tee boxes_driving | 
+| 11 | golfer - great golfer - awesome president - trump golfer - video president | 409 | 11_golfer_great golfer_awesome president_trump golfer | 
+| 12 | best video - video best - youtube video - greatest video - video greatest | 404 | 12_best video_video best_youtube video_greatest video | 
+| 13 | golf bryson - thank bryson - bryson president - thank - trump bryson | 393 | 13_golf bryson_thank bryson_bryson president_thank | 
+| 14 | golfer trump - golf trump - good golfer - good golf - golfer | 376 | 14_golfer trump_golf trump_good golfer_good golf | 
+| 15 | got game - game trump - trump game - trump got - trump play | 359 | 15_got game_game trump_trump game_trump got | 
+| 16 | president president - ex - referred - ex president - president ex | 359 | 16_president president_ex_referred_ex president | 
+| 17 | awesome video - video trump - great video - video maga - best video | 340 | 17_awesome video_video trump_great video_video maga | 
+| 18 | armed golfer - biden armed - biden brooks - epic lfg - dope yessirr | 314 | 18_armed golfer_biden armed_biden brooks_epic lfg | 
+| 19 | ad - kamala - kamala harris - ads - harris | 302 | 19_ad_kamala_kamala harris_ads | 
+| 20 | media - evil - hate - ran - persona | 292 | 20_media_evil_hate_ran | 
+| 21 | internet - break internet - gonna break - trending - internet break | 275 | 21_internet_break internet_gonna break_trending | 
+| 22 | stroke - putting stroke - trumps putting - putting - trump putting | 234 | 22_stroke_putting stroke_trumps putting_putting | 
+| 23 | bryson bryson - let bryson - bryson man - love bryson - bryson knows | 229 | 23_bryson bryson_let bryson_bryson man_love bryson | 
+| 24 | solo - eagle - solo eagle - solo birdie - trump solo | 225 | 24_solo_eagle_solo eagle_solo birdie | 
+| 25 | carts - secret service - golf carts - secret - service | 205 | 25_carts_secret service_golf carts_secret | 
+| 26 | neville - neville neville - neville needs - neville vp - shoutout neville | 204 | 26_neville_neville neville_neville needs_neville vp | 
+| 27 | mbellracing - mbellracing bye - mbellracing mbellracing - bye - announce | 204 | 27_mbellracing_mbellracing bye_mbellracing mbellracing_bye | 
+| 28 | trump inside - inside - president inside - inside president - inside looks | 195 | 28_trump inside_inside_president inside_inside president | 
+| 29 | partner - partner partner - partner counter - counter - partner count | 170 | 29_partner_partner partner_partner counter_counter | 
+| 30 | hell yeah - yes - yes hell - yes yes - hell yes | 164 | 30_hell yeah_yes_yes hell_yes yes | 
+| 31 | putting stroke - stroke - putting - stroke putting - wtf putting | 159 | 31_putting stroke_stroke_putting_stroke putting | 
+| 32 | trump 2024 - 2024 - 2024 trump - baby - 2024 baby | 146 | 32_trump 2024_2024_2024 trump_baby | 
+| 33 | par - par 210 - yard par - 210 - yds | 142 | 33_par_par 210_yard par_210 | 
+| 34 | age - good age - player play - expect good - age man | 141 | 34_age_good age_player play_expect good | 
+| 35 | 32 - 32 53 - 32 52 - pause - 52 | 140 | 35_32_32 53_32 52_pause | 
+| 36 | brooks - tiger - scottie - charles barkley - charles | 140 | 36_brooks_tiger_scottie_charles barkley | 
+| 37 | need therapy - sad - pouty - friendless - mind gutter | 139 | 37_need therapy_sad_pouty_friendless | 
+| 38 | brainwashed - media brainwashed - mainstream - mainstream media - propaganda | 137 | 38_brainwashed_media brainwashed_mainstream_mainstream media | 
+| 39 | watch fun - fun watch - fun - entertaining fun - watch | 135 | 39_watch fun_fun watch_fun_entertaining fun | 
+| 40 | congrats bryson - congrats - bryson congrats - bryson million - subscribers bryson | 129 | 40_congrats bryson_congrats_bryson congrats_bryson million | 
+| 41 | wait - wait watch - wait gonna - gonna epic - ve waiting | 129 | 41_wait_wait watch_wait gonna_gonna epic | 
+| 42 | trump looks - looks old - looks - breath - really old | 127 | 42_trump looks_looks old_looks_breath | 
+| 43 | watched golf - golf entertaining - watch golf - golf watched - like golf | 122 | 43_watched golf_golf entertaining_watch golf_golf watched | 
+| 44 | playlist - song - johnny cash - bocelli - music | 120 | 44_playlist_song_johnny cash_bocelli | 
+| 45 | way way - cringe - cringe cringe - gross - disappointing | 118 | 45_way way_cringe_cringe cringe_gross | 
+| 46 | insane - unbelievable - insane wild - wild unreal - unbelievable unbelievable | 112 | 46_insane_unbelievable_insane wild_wild unreal | 
+| 47 | break 50 - 50 - break - 50 break - breaking 50 | 110 | 47_break 50_50_break_50 break | 
+| 48 | 2019 - wounded - 2018 - 2019 trump - veterans | 110 | 48_2019_wounded_2018_2019 trump | 
+| 49 | looks old - 78 - old - turned 78 - old needs | 108 | 49_looks old_78_old_turned 78 | 
+| 50 | baperacks - com6801 - baperacks com6801 - com6801this - baperacks com6801this | 107 | 50_baperacks_com6801_baperacks com6801_com6801this | 
+| 51 | holes president - gotten inside - president gotten - gotten - holes | 107 | 51_holes president_gotten inside_president gotten_gotten | 
+| 52 | trump love - love trump - love president - love mr - man love | 100 | 52_trump love_love trump_love president_love mr | 
+| 53 | 47 - shoot 47 - 47 47 - score 47 - 45 | 89 | 53_47_shoot 47_47 47_score 47 | 
+| 54 | gets inside - trump gets - 14 president - inside don - know going | 86 | 54_gets inside_trump gets_14 president_inside don | 
+| 55 | round - great round - round awesome - round great - round round | 86 | 55_round_great round_round awesome_round great | 
+| 56 | golf make - make golf - america golf - great make - golf great | 85 | 56_golf make_make golf_america golf_great make | 
+| 57 | ladies - tees - ladies tees - red tees - playing ladies | 83 | 57_ladies_tees_ladies tees_red tees | 
+| 58 | episode - episode great - great episode - best episode - legendary episode | 83 | 58_episode_episode great_great episode_best episode | 
+| 59 | nice trump - enjoying time - human nice - setting love - seeing president | 78 | 59_nice trump_enjoying time_human nice_setting love | 
+| 60 | gooooo - goooooo - gooooo let - goooooo let - lets gooooo | 76 | 60_gooooo_goooooo_gooooo let_goooooo let | 
+| 61 | reed - patrick reed - patrick - likes patrick - reed trump | 76 | 61_reed_patrick reed_patrick_likes patrick | 
+| 62 | let let - let lets - let - lets let - let fucking | 76 | 62_let let_let lets_let_lets let | 
+| 63 | duo - favorite people - best duo - duo best - better duo | 73 | 63_duo_favorite people_best duo_duo best | 
+| 64 | racist - trump racist - black - racist trump - racist black | 73 | 64_racist_trump racist_black_racist trump | 
+| 65 | dechambeau - trump dechambeau - dechambeau 2024 - dechambeau trump - 2024 dechambeau | 73 | 65_dechambeau_trump dechambeau_dechambeau 2024_dechambeau trump | 
+| 66 | video bryson - bryson great - bryson awesome - thanks bryson - truly great | 72 | 66_video bryson_bryson great_bryson awesome_thanks bryson | 
+| 67 | wet mr - wet - president wet - president 17 - mr president | 71 | 67_wet mr_wet_president wet_president 17 | 
+| 68 | rapist - golfing rapist - felon - rapist felon - felon playing | 71 | 68_rapist_golfing rapist_felon_rapist felon | 
+| 69 | tds - tds tds - tds showing - real tds - tds real | 69 | 69_tds_tds tds_tds showing_real tds | 
+| 70 | bryson bryson - disappointing bryson - respect anymore - bryson sorry - ya bryson | 68 | 70_bryson bryson_disappointing bryson_respect anymore_bryson sorry | 
+| 71 | grant - grant grant - sorry grant - grant afraid - lost race | 67 | 71_grant_grant grant_sorry grant_grant afraid | 
+| 72 | subscribed - subscribe - subscriber - just subscribed - earned subscriber | 65 | 72_subscribed_subscribe_subscriber_just subscribed | 
+| 73 | driver - driver trumps - driving - trumps drive - trumps driving | 65 | 73_driver_driver trumps_driving_trumps drive | 
+| 74 | does drop - dropping - drop - drop dropping - dropping does | 64 | 74_does drop_dropping_drop_drop dropping | 
+| 75 | lfg - lfg lfg - lfg holy - lfg trump - yes lfg | 62 | 75_lfg_lfg lfg_lfg holy_lfg trump | 
+| 76 | fist - bump - fist bump - bump high - high fist | 62 | 76_fist_bump_fist bump_bump high | 
+| 77 | djt - dt - djt real - djt really - great dt | 61 | 77_djt_dt_djt real_djt really | 
+| 78 | goats - goat goat - goat - goats goats - goat goats | 59 | 78_goats_goat goat_goat_goats goats | 
+| 79 | great game - match amazing - love game - fun love - having fun | 59 | 79_great game_match amazing_love game_fun love | 
+| 80 | drinking game - drink time - drink - say partner - shot time | 58 | 80_drinking game_drink time_drink_say partner | 
+| 81 | usa usa - usa - bless america - usa america - severe braggadocious | 57 | 81_usa usa_usa_bless america_usa america | 
+| 82 | course course - course - course short - course know - short course | 56 | 82_course course_course_course short_course know | 
+| 83 | bryson lost - shame bryson - fraud criminal - forced penetration - penetration | 56 | 83_bryson lost_shame bryson_fraud criminal_forced penetration | 
+| 84 | exercise routine - good entertainment - like style - entire exercise - bryson nearly | 55 | 84_exercise routine_good entertainment_like style_entire exercise | 
+| 85 | tracer - red white - tracers - white blue - walking tracer | 55 | 85_tracer_red white_tracers_white blue | 
+| 86 | 1000 - win 1000 - 1k - ll donate - ll 1k | 54 | 86_1000_win 1000_1k_ll donate | 
+| 87 | comment - best comment - comment best - comment year - comment section | 53 | 87_comment_best comment_comment best_comment year | 
+| 88 | collab - best collab - greatest collab - collab best - needed | 53 | 88_collab_best collab_greatest collab_collab best | 
+| 89 | rapist - felon - sexual - convicted - sexual predator | 53 | 89_rapist_felon_sexual_convicted | 
+| 90 | felon - convicted felon - convicted - impeached - twice impeached | 53 | 90_felon_convicted felon_convicted_impeached | 
+| 91 | 24сағат - 24сағат орындықта - 𝑻𝑹𝑼𝑴𝑷 ىباتياز - ىباتياز wwwwww - ىباتياز | 51 | 91_24сағат_24сағат орындықта_𝑻𝑹𝑼𝑴𝑷 ىباتياز_ىباتياز wwwwww | 
+| 92 | trees - maple - grows - grow naturally - love trees | 51 | 92_trees_maple_grows_grow naturally | 
+| 93 | jordan - michael jordan - michael - jordan michael - curry michael | 51 | 93_jordan_michael jordan_michael_jordan michael | 
+| 94 | susan - jane - susan jane - investing - tithing | 50 | 94_susan_jane_susan jane_investing | 
+| 95 | tyt - sucks golf - newsweek trump - trump sucks - misses 12 | 50 | 95_tyt_sucks golf_newsweek trump_trump sucks | 
+| 96 | great cause - donate great - cause - 220k - charity | 49 | 96_great cause_donate great_cause_220k | 
+| 97 | unfollow - unfollowing - unfollowed - unfollow unfollow - unfollowed bye | 48 | 97_unfollow_unfollowing_unfollowed_unfollow unfollow | 
+| 98 | cheats - cheat - cheats cheats - cheater cheats - stories cheating | 48 | 98_cheats_cheat_cheats cheats_cheater cheats | 
+| 99 | subscribed - subscribing - sub trump - got subscription - trump subscribed | 46 | 99_subscribed_subscribing_sub trump_got subscription | 
+| 100 | thats president - president thats - president president - president canadian - canadian | 46 | 100_thats president_president thats_president president_president canadian | 
+| 101 | fans value - write admired - betrayal fans - golf deeply - continue supporting | 44 | 101_fans value_write admired_betrayal fans_golf deeply | 
+| 102 | long straight - known long - known - long - straight | 42 | 102_long straight_known long_known_long | 
+| 103 | biden break - 50 biden - biden breaking - break 120 - 120 | 42 | 103_biden break_50 biden_biden breaking_break 120 | 
+| 104 | break 50 - way break - trump break - mean break - felonies sure | 40 | 104_break 50_way break_trump break_mean break | 
+| 105 | crying liberal - crying - whaaa - harder liberal - harder | 39 | 105_crying liberal_crying_whaaa_harder liberal | 
+| 106 | look like - looks different - really look - really trump - doesn look | 39 | 106_look like_looks different_really look_really trump | 
+| 107 | gets inside - trump gets - inside don - know going - going president | 38 | 107_gets inside_trump gets_inside don_know going | 
+| 108 | 10 alex - amazingggggg - alex literally - amazingggggg internet - haaaaaaaaaa | 38 | 108_10 alex_amazingggggg_alex literally_amazingggggg internet | 
+| 109 | trump voting - wait vote - vote president - trump wait - forever spain | 37 | 109_trump voting_wait vote_vote president_trump wait | 
+| 110 | jesus - evolution - finally - animals - god | 37 | 110_jesus_evolution_finally_animals | 
+| 111 | editing - edited - edited edited - heavily edited - magic scripts | 36 | 111_editing_edited_edited edited_heavily edited | 
+| 112 | nicholasfago1025 - crushersgc - abesapien9930 locoade87 - absolute lightwork - crushersgc maga | 35 | 112_nicholasfago1025_crushersgc_abesapien9930 locoade87_absolute lightwork | 
+| 113 | bedminster - bedminster nj - nj - national bedminster - nj bedminster | 35 | 113_bedminster_bedminster nj_nj_national bedminster | 
+| 114 | didn tougher - race - just ended - ended - tougher | 35 | 114_didn tougher_race_just ended_ended | 
+| 115 | owns place - does place - place - joint - owns | 34 | 115_owns place_does place_place_joint | 
+| 116 | goooooo let - gooooooo let - gooooo let - let goooooo - let gooooo | 33 | 116_goooooo let_gooooooo let_gooooo let_let goooooo | 
+| 117 | seethe cope - cope seethe - seethe - cope - brother cope | 32 | 117_seethe cope_cope seethe_seethe_cope | 
+| 118 | turnberry - course world - turnberry ranked - ranked - rated | 31 | 118_turnberry_course world_turnberry ranked_ranked | 
+| 119 | knew liked - like knew - knew loved - liked - love knew | 31 | 119_knew liked_like knew_knew loved_liked | 
+| 120 | content - content content - cool content - great content - content man | 30 | 120_content_content content_cool content_great content | 
+| 121 | white house - potus crap - good spent - course white - house | 29 | 121_white house_potus crap_good spent_course white | 
+| 122 | bag - trump bag - bag need - trumps bag - need bag | 29 | 122_bag_trump bag_bag need_trumps bag | 
+| 123 | maga maga - great maga - maga - make america - america great | 29 | 123_maga maga_great maga_maga_make america | 
+| 124 | 2024 trump - trump trump - 2024 grant - trump único - trump trumppppppp | 28 | 124_2024 trump_trump trump_2024 grant_trump único | 
+| 125 | 6th tf - ago happened - bum jan - bullying feel - didn day | 28 | 125_6th tf_ago happened_bum jan_bullying feel | 
+| 126 | 47 hat - hat - 45 47 - hat 45 - 47 | 28 | 126_47 hat_hat_45 47_hat 45 | 
+| 127 | med - att - jag - öl med - 80 goat | 28 | 127_med_att_jag_öl med | 
+| 128 | trump god - god bless - bless - bless president - god | 27 | 128_trump god_god bless_bless_bless president | 
+| 129 | golf etiquette - tell lot - anybody regular - age knows - age grandpa | 27 | 129_golf etiquette_tell lot_anybody regular_age knows | 
+| 130 | younger biden - age - 78 insanely - 2024 win - truly skilled | 27 | 130_younger biden_age_78 insanely_2024 win | 
+| 131 | diet coke - diet - coke - glass - bottle | 27 | 131_diet coke_diet_coke_glass | 
+| 132 | 78 - play 78 - old hit - hope play - like 78 | 26 | 132_78_play 78_old hit_hope play |
+
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: True
+* language: None
+* low_memory: False
+* min_topic_size: 10
+* n_gram_range: (1, 1)
+* nr_topics: None
+* seed_topic_list: None
+* top_n_words: 10
+* verbose: True
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 2.0.2
+* HDBSCAN: 0.8.40
+* UMAP: 0.5.7
+* Pandas: 2.2.2
+* Scikit-Learn: 1.6.1
+* Sentence-transformers: 3.4.1
+* Transformers: 4.51.3
+* Numba: 0.60.0
+* Plotly: 5.24.1
+* Python: 3.11.12

config.json

@@ -0,0 +1,16 @@
+{
+  "calculate_probabilities": true,
+  "language": null,
+  "low_memory": false,
+  "min_topic_size": 10,
+  "n_gram_range": [
+    1,
+    1
+  ],
+  "nr_topics": null,
+  "seed_topic_list": null,
+  "top_n_words": 10,
+  "verbose": true,
+  "zeroshot_min_similarity": 0.7,
+  "zeroshot_topic_list": null
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efbdb342d16ee6f57c52acbc32ba32f0e1cb63194d64b196f411039ee9c1db6
+size 6437664

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d13e37f083023989fe1d6b68d5f6de4027b0466d2144883d0f52ac90ae1f1a
+size 548960