Hugging Face's logo

mcllstr
/
setfit-mltclss

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Eval Results
Model card Files Community
2
mcllstr commited on
Commit
38ebbdd
•
1 Parent(s): e667943

Push model using huggingface_hub.

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +0 -0
  3. config.json +26 -0
  4. config_sentence_transformers.json +9 -0
  5. config_setfit.json +224 -0
  6. model.safetensors +3 -0
  7. model_head.pkl +3 -0
  8. modules.json +20 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +37 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +64 -0
  13. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.0.dev0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.6.1",
5
+ "pytorch": "1.8.1"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
config_setfit.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "normalize_embeddings": false,
3
+ "labels": [
4
+ "AgentActorAdultActor",
5
+ "AgentActorVoiceActor",
6
+ "AgentArtistComedian",
7
+ "AgentArtistComicsCreator",
8
+ "AgentArtistFashionDesigner",
9
+ "AgentArtistPainter",
10
+ "AgentArtistPhotographer",
11
+ "AgentAthleteAustralianRulesFootballPlayer",
12
+ "AgentAthleteBadmintonPlayer",
13
+ "AgentAthleteBaseballPlayer",
14
+ "AgentAthleteBasketballPlayer",
15
+ "AgentAthleteBodybuilder",
16
+ "AgentAthleteCanoeist",
17
+ "AgentAthleteChessPlayer",
18
+ "AgentAthleteCricketer",
19
+ "AgentAthleteCyclist",
20
+ "AgentAthleteDartsPlayer",
21
+ "AgentAthleteGaelicGamesPlayer",
22
+ "AgentAthleteGolfPlayer",
23
+ "AgentAthleteGymnast",
24
+ "AgentAthleteHandballPlayer",
25
+ "AgentAthleteHorseRider",
26
+ "AgentAthleteJockey",
27
+ "AgentAthleteLacrossePlayer",
28
+ "AgentAthleteMartialArtist",
29
+ "AgentAthleteNetballPlayer",
30
+ "AgentAthletePokerPlayer",
31
+ "AgentAthleteRower",
32
+ "AgentAthleteRugbyPlayer",
33
+ "AgentAthleteSoccerPlayer",
34
+ "AgentAthleteSquashPlayer",
35
+ "AgentAthleteSwimmer",
36
+ "AgentAthleteTableTennisPlayer",
37
+ "AgentAthleteTennisPlayer",
38
+ "AgentBoxerAmateurBoxer",
39
+ "AgentBritishRoyaltyBaronet",
40
+ "AgentBroadcasterBroadcastNetwork",
41
+ "AgentBroadcasterRadioStation",
42
+ "AgentBroadcasterTelevisionStation",
43
+ "AgentClericCardinal",
44
+ "AgentClericChristianBishop",
45
+ "AgentClericPope",
46
+ "AgentClericSaint",
47
+ "AgentCoachCollegeCoach",
48
+ "AgentComicsCharacterAnimangaCharacter",
49
+ "AgentCompanyAirline",
50
+ "AgentCompanyBank",
51
+ "AgentCompanyBrewery",
52
+ "AgentCompanyBusCompany",
53
+ "AgentCompanyLawFirm",
54
+ "AgentCompanyPublisher",
55
+ "AgentCompanyRecordLabel",
56
+ "AgentCompanyWinery",
57
+ "AgentEducationalInstitutionLibrary",
58
+ "AgentEducationalInstitutionSchool",
59
+ "AgentEducationalInstitutionUniversity",
60
+ "AgentFictionalCharacterMythologicalFigure",
61
+ "AgentFictionalCharacterSoapCharacter",
62
+ "AgentGridironFootballPlayerAmericanFootballPlayer",
63
+ "AgentGroupBand",
64
+ "AgentMotorcycleRiderSpeedwayRider",
65
+ "AgentMusicalArtistClassicalMusicArtist",
66
+ "AgentOrganisationLegislature",
67
+ "AgentOrganisationMemberSportsTeamMember",
68
+ "AgentOrganisationMilitaryUnit",
69
+ "AgentOrganisationPoliticalParty",
70
+ "AgentOrganisationPublicTransitSystem",
71
+ "AgentOrganisationTradeUnion",
72
+ "AgentPersonAmbassador",
73
+ "AgentPersonArchitect",
74
+ "AgentPersonAstronaut",
75
+ "AgentPersonBeautyQueen",
76
+ "AgentPersonBusinessPerson",
77
+ "AgentPersonChef",
78
+ "AgentPersonEconomist",
79
+ "AgentPersonEngineer",
80
+ "AgentPersonHorseTrainer",
81
+ "AgentPersonJournalist",
82
+ "AgentPersonJudge",
83
+ "AgentPersonMilitaryPerson",
84
+ "AgentPersonModel",
85
+ "AgentPersonMonarch",
86
+ "AgentPersonNoble",
87
+ "AgentPersonOfficeHolder",
88
+ "AgentPersonPhilosopher",
89
+ "AgentPersonPlayboyPlaymate",
90
+ "AgentPersonReligious",
91
+ "AgentPoliticianCongressman",
92
+ "AgentPoliticianGovernor",
93
+ "AgentPoliticianMayor",
94
+ "AgentPoliticianMemberOfParliament",
95
+ "AgentPoliticianPresident",
96
+ "AgentPoliticianPrimeMinister",
97
+ "AgentPoliticianSenator",
98
+ "AgentPresenterRadioHost",
99
+ "AgentRacingDriverFormulaOneRacer",
100
+ "AgentRacingDriverNascarDriver",
101
+ "AgentScientistEntomologist",
102
+ "AgentScientistMedician",
103
+ "AgentSportsLeagueBaseballLeague",
104
+ "AgentSportsLeagueBasketballLeague",
105
+ "AgentSportsLeagueIceHockeyLeague",
106
+ "AgentSportsLeagueRugbyLeague",
107
+ "AgentSportsLeagueSoccerLeague",
108
+ "AgentSportsManagerSoccerManager",
109
+ "AgentSportsTeamAustralianFootballTeam",
110
+ "AgentSportsTeamBasketballTeam",
111
+ "AgentSportsTeamCanadianFootballTeam",
112
+ "AgentSportsTeamCricketTeam",
113
+ "AgentSportsTeamCyclingTeam",
114
+ "AgentSportsTeamHandballTeam",
115
+ "AgentSportsTeamHockeyTeam",
116
+ "AgentSportsTeamRugbyClub",
117
+ "AgentVolleyballPlayerBeachVolleyballPlayer",
118
+ "AgentWinterSportPlayerCurler",
119
+ "AgentWinterSportPlayerFigureSkater",
120
+ "AgentWinterSportPlayerIceHockeyPlayer",
121
+ "AgentWinterSportPlayerSkater",
122
+ "AgentWinterSportPlayerSkier",
123
+ "AgentWrestlerSumoWrestler",
124
+ "AgentWriterHistorian",
125
+ "AgentWriterPoet",
126
+ "AgentWriterScreenWriter",
127
+ "DeviceEngineAutomobileEngine",
128
+ "EventNaturalEventEarthquake",
129
+ "EventNaturalEventSolarEclipse",
130
+ "EventOlympicsOlympicEvent",
131
+ "EventRaceCyclingRace",
132
+ "EventRaceHorseRace",
133
+ "EventSocietalEventConvention",
134
+ "EventSocietalEventElection",
135
+ "EventSocietalEventFilmFestival",
136
+ "EventSocietalEventMilitaryConflict",
137
+ "EventSocietalEventMusicFestival",
138
+ "EventSportsEventFootballMatch",
139
+ "EventSportsEventGrandPrix",
140
+ "EventSportsEventMixedMartialArtsEvent",
141
+ "EventSportsEventWrestlingEvent",
142
+ "EventTournamentGolfTournament",
143
+ "EventTournamentSoccerTournament",
144
+ "EventTournamentTennisTournament",
145
+ "EventTournamentWomensTennisAssociationTournament",
146
+ "PlaceAmusementParkAttractionRollerCoaster",
147
+ "PlaceBodyOfWaterLake",
148
+ "PlaceBuildingCastle",
149
+ "PlaceBuildingHistoricBuilding",
150
+ "PlaceBuildingHospital",
151
+ "PlaceBuildingHotel",
152
+ "PlaceBuildingMuseum",
153
+ "PlaceBuildingPrison",
154
+ "PlaceBuildingRestaurant",
155
+ "PlaceBuildingShoppingMall",
156
+ "PlaceCelestialBodyGalaxy",
157
+ "PlaceCelestialBodyPlanet",
158
+ "PlaceClericalAdministrativeRegionDiocese",
159
+ "PlaceInfrastructureAirport",
160
+ "PlaceInfrastructureDam",
161
+ "PlaceNaturalPlaceCave",
162
+ "PlaceNaturalPlaceGlacier",
163
+ "PlaceNaturalPlaceMountain",
164
+ "PlaceNaturalPlaceMountainPass",
165
+ "PlaceNaturalPlaceMountainRange",
166
+ "PlaceNaturalPlaceVolcano",
167
+ "PlaceRaceTrackRacecourse",
168
+ "PlaceRouteOfTransportationBridge",
169
+ "PlaceRouteOfTransportationRailwayLine",
170
+ "PlaceRouteOfTransportationRoad",
171
+ "PlaceRouteOfTransportationRoadTunnel",
172
+ "PlaceSatelliteArtificialSatellite",
173
+ "PlaceSettlementTown",
174
+ "PlaceSettlementVillage",
175
+ "PlaceSportFacilityCricketGround",
176
+ "PlaceSportFacilityGolfCourse",
177
+ "PlaceSportFacilityStadium",
178
+ "PlaceStationRailwayStation",
179
+ "PlaceStreamCanal",
180
+ "PlaceStreamRiver",
181
+ "PlaceTowerLighthouse",
182
+ "PlaceVenueTheatre",
183
+ "SpeciesAnimalAmphibian",
184
+ "SpeciesAnimalArachnid",
185
+ "SpeciesAnimalBird",
186
+ "SpeciesAnimalCrustacean",
187
+ "SpeciesAnimalFish",
188
+ "SpeciesAnimalInsect",
189
+ "SpeciesAnimalMollusca",
190
+ "SpeciesAnimalReptile",
191
+ "SpeciesEukaryoteFungus",
192
+ "SpeciesFloweringPlantGrape",
193
+ "SpeciesHorseRaceHorse",
194
+ "SpeciesPlantConifer",
195
+ "SpeciesPlantCultivatedVariety",
196
+ "SpeciesPlantCycad",
197
+ "SpeciesPlantFern",
198
+ "SpeciesPlantGreenAlga",
199
+ "SpeciesPlantMoss",
200
+ "SportsSeasonFootballLeagueSeasonNationalFootballLeagueSeason",
201
+ "SportsSeasonSportsTeamSeasonBaseballSeason",
202
+ "SportsSeasonSportsTeamSeasonNCAATeamSeason",
203
+ "SportsSeasonSportsTeamSeasonSoccerClubSeason",
204
+ "TopicalConceptGenreMusicGenre",
205
+ "UnitOfWorkLegalCaseSupremeCourtOfTheUnitedStatesCase",
206
+ "WorkCartoonAnime",
207
+ "WorkCartoonHollywoodCartoon",
208
+ "WorkComicComicStrip",
209
+ "WorkComicManga",
210
+ "WorkDatabaseBiologicalDatabase",
211
+ "WorkMusicalWorkAlbum",
212
+ "WorkMusicalWorkArtistDiscography",
213
+ "WorkMusicalWorkClassicalMusicComposition",
214
+ "WorkMusicalWorkMusical",
215
+ "WorkMusicalWorkSingle",
216
+ "WorkPeriodicalLiteratureAcademicJournal",
217
+ "WorkPeriodicalLiteratureMagazine",
218
+ "WorkPeriodicalLiteratureNewspaper",
219
+ "WorkSoftwareVideoGame",
220
+ "WorkSongEurovisionSongContestEntry",
221
+ "WorkWrittenWorkPlay",
222
+ "WorkWrittenWorkPoem"
223
+ ]
224
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794472ed4c13906c0ed7d5dda2569bb293b66c60a1caa1e461922f94d8b2d37c
3
+ size 90864192
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75af33ab017b25ac08570fc8840b112ba25bf2d8a034370b6b39137f317b6cfd
3
+ size 677119
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 256,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 128,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff