Add BERTopic model

README.md

@@ -0,0 +1,95 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+---
+
+# BERTopic_Multimodal
+
+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("MaartenGr/BERTopic_Multimodal")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 29
+* Number of training documents: 8091
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | while - air - the - in - jumping | 34 | -1_while_air_the_in | 
+| 0 | bench - sitting - people - woman - street | 1132 | 0_bench_sitting_people_woman | 
+| 1 | grass - running - dog - grassy - field | 1693 | 1_grass_running_dog_grassy | 
+| 2 | boy - girl - little - young - holding | 1290 | 2_boy_girl_little_young | 
+| 3 | dog - frisbee - running - water - mouth | 1224 | 3_dog_frisbee_running_water | 
+| 4 | skateboard - ramp - doing - trick - cement | 415 | 4_skateboard_ramp_doing_trick | 
+| 5 | snow - dog - covered - running - through | 309 | 5_snow_dog_covered_running | 
+| 6 | mountain - range - slope - standing - person | 205 | 6_mountain_range_slope_standing | 
+| 7 | pool - blue - boy - toy - water | 189 | 7_pool_blue_boy_toy | 
+| 8 | trail - bike - down - riding - person | 166 | 8_trail_bike_down_riding | 
+| 9 | snowboarder - mid - jump - air - after | 126 | 9_snowboarder_mid_jump_air | 
+| 10 | rock - climbing - up - wall - tree | 124 | 10_rock_climbing_up_wall | 
+| 11 | wave - surfboard - top - riding - of | 112 | 11_wave_surfboard_top_riding | 
+| 12 | beach - surfboard - people - with - walking | 102 | 12_beach_surfboard_people_with | 
+| 13 | jumping - track - horse - racquet - dog | 98 | 13_jumping_track_horse_racquet | 
+| 14 | snowboard - snow - girl - hill - slope | 95 | 14_snowboard_snow_girl_hill | 
+| 15 | game - being - football - played - professional | 91 | 15_game_being_football_played | 
+| 16 | soccer - kicking - team - ball - player | 80 | 16_soccer_kicking_team_ball | 
+| 17 | dirt - bike - person - rider - going | 75 | 17_dirt_bike_person_rider | 
+| 18 | soccer - boys - field - ball - kicking | 69 | 18_soccer_boys_field_ball | 
+| 19 | baseball - player - bat - swinging - into | 63 | 19_baseball_player_bat_swinging | 
+| 20 | basketball - up - and - playing - jumping | 59 | 20_basketball_up_and_playing | 
+| 21 | bird - body - flying - over - long | 55 | 21_bird_body_flying_over | 
+| 22 | motorcycle - track - race - racer - racing | 55 | 22_motorcycle_track_race_racer | 
+| 23 | boat - sitting - water - lake - hose | 53 | 23_boat_sitting_water_lake | 
+| 24 | street - riding - down - bike - woman | 52 | 24_street_riding_down_bike | 
+| 25 | paddle - suit - paddling - water - in | 49 | 25_paddle_suit_paddling_water | 
+| 26 | pair - scissors - stage - white - shirt | 42 | 26_pair_scissors_stage_white | 
+| 27 | tennis - court - racket - racquet - swinging | 34 | 27_tennis_court_racket_racquet |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: None
+* low_memory: False
+* min_topic_size: 30
+* n_gram_range: (1, 1)
+* nr_topics: None
+* seed_topic_list: None
+* top_n_words: 10
+* verbose: True
+
+## Framework versions
+
+* Numpy: 1.23.5
+* HDBSCAN: 0.8.29
+* UMAP: 0.5.3
+* Pandas: 1.5.3
+* Scikit-Learn: 1.2.2
+* Sentence-transformers: 2.2.2
+* Transformers: 4.29.2
+* Numba: 0.56.4
+* Plotly: 5.14.1
+* Python: 3.10.10

config.json

@@ -0,0 +1,14 @@
+{
+  "calculate_probabilities": false,
+  "language": null,
+  "low_memory": false,
+  "min_topic_size": 30,
+  "n_gram_range": [
+    1,
+    1
+  ],
+  "nr_topics": null,
+  "seed_topic_list": null,
+  "top_n_words": 10,
+  "verbose": true
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465603b0624b3ee3419120940aaf719522f68ab182a3e29e63a1d48381cfd2c1
+size 10240

ctfidf_config.json

@@ -0,0 +1,237 @@
+{
+  "ctfidf_model": {
+    "bm25_weighting": false,
+    "reduce_frequent_words": false
+  },
+  "vectorizer_model": {
+    "params": {
+      "analyzer": "word",
+      "binary": false,
+      "decode_error": "strict",
+      "encoding": "utf-8",
+      "input": "content",
+      "lowercase": true,
+      "max_df": 1.0,
+      "max_features": null,
+      "min_df": 1,
+      "ngram_range": [
+        1,
+        1
+      ],
+      "stop_words": null,
+      "strip_accents": null,
+      "token_pattern": "(?u)\\b\\w\\w+\\b",
+      "vocabulary": null
+    },
+    "vocab": {
+      "woman": 203,
+      "is": 85,
+      "playing": 131,
+      "with": 202,
+      "frisbee": 60,
+      "on": 113,
+      "the": 176,
+      "beach": 17,
+      "man": 101,
+      "in": 83,
+      "blue": 28,
+      "shirt": 152,
+      "water": 196,
+      "young": 207,
+      "boy": 33,
+      "wet": 198,
+      "suit": 169,
+      "standing": 166,
+      "person": 124,
+      "jumping": 91,
+      "air": 2,
+      "while": 199,
+      "holding": 78,
+      "surfboard": 171,
+      "rock": 148,
+      "climbing": 44,
+      "wall": 193,
+      "two": 188,
+      "boys": 34,
+      "are": 7,
+      "to": 179,
+      "catch": 39,
+      "walking": 192,
+      "down": 52,
+      "street": 167,
+      "cell": 40,
+      "phone": 125,
+      "crowd": 47,
+      "of": 112,
+      "people": 122,
+      "sitting": 153,
+      "bench": 21,
+      "outside": 116,
+      "building": 36,
+      "talking": 173,
+      "next": 110,
+      "group": 69,
+      "dog": 49,
+      "bird": 26,
+      "her": 73,
+      "head": 72,
+      "running": 150,
+      "grass": 66,
+      "through": 177,
+      "grassy": 67,
+      "field": 56,
+      "dogs": 50,
+      "each": 54,
+      "other": 114,
+      "across": 0,
+      "and": 5,
+      "cat": 38,
+      "its": 87,
+      "mouth": 108,
+      "black": 27,
+      "brown": 35,
+      "girl": 63,
+      "hugging": 82,
+      "baseball": 14,
+      "bat": 16,
+      "his": 75,
+      "hand": 70,
+      "little": 99,
+      "red": 143,
+      "umbrella": 189,
+      "metal": 103,
+      "pole": 132,
+      "wooden": 205,
+      "bed": 19,
+      "skateboard": 154,
+      "middle": 105,
+      "park": 121,
+      "throwing": 178,
+      "hill": 74,
+      "ball": 11,
+      "along": 4,
+      "body": 31,
+      "skateboarder": 155,
+      "doing": 51,
+      "trick": 187,
+      "ramp": 140,
+      "riding": 145,
+      "top": 182,
+      "cement": 41,
+      "bike": 24,
+      "snow": 159,
+      "covered": 46,
+      "snowboard": 160,
+      "snowy": 163,
+      "surface": 170,
+      "slope": 158,
+      "tongue": 181,
+      "out": 115,
+      "laying": 97,
+      "fighting": 57,
+      "over": 117,
+      "ground": 68,
+      "jacket": 88,
+      "mountain": 107,
+      "range": 141,
+      "up": 191,
+      "backpack": 10,
+      "skis": 156,
+      "children": 43,
+      "pool": 133,
+      "toy": 183,
+      "baby": 9,
+      "board": 29,
+      "white": 200,
+      "boogie": 32,
+      "dirt": 48,
+      "trail": 185,
+      "snowboarder": 161,
+      "pile": 126,
+      "mid": 104,
+      "after": 1,
+      "jump": 90,
+      "airborne": 3,
+      "going": 65,
+      "tree": 186,
+      "near": 109,
+      "rope": 149,
+      "wave": 197,
+      "ocean": 111,
+      "track": 184,
+      "horse": 80,
+      "racquet": 139,
+      "pair": 120,
+      "jockeys": 89,
+      "racing": 137,
+      "race": 135,
+      "rider": 144,
+      "snowboarding": 162,
+      "child": 42,
+      "football": 59,
+      "game": 61,
+      "being": 20,
+      "played": 128,
+      "during": 53,
+      "player": 129,
+      "plate": 127,
+      "professional": 134,
+      "soccer": 164,
+      "team": 174,
+      "watching": 195,
+      "large": 96,
+      "men": 102,
+      "kicking": 94,
+      "getting": 62,
+      "ready": 142,
+      "kick": 93,
+      "road": 147,
+      "sliding": 157,
+      "into": 84,
+      "home": 79,
+      "another": 6,
+      "watches": 194,
+      "swinging": 172,
+      "base": 13,
+      "at": 8,
+      "uniform": 190,
+      "basketball": 15,
+      "players": 130,
+      "hit": 76,
+      "court": 45,
+      "hitting": 77,
+      "flying": 58,
+      "long": 100,
+      "beak": 18,
+      "motorcycle": 106,
+      "racer": 136,
+      "boat": 30,
+      "paddling": 119,
+      "canoe": 37,
+      "lake": 95,
+      "hat": 71,
+      "paddle": 118,
+      "river": 146,
+      "bank": 12,
+      "hose": 81,
+      "women": 204,
+      "bicycles": 23,
+      "bicycle": 22,
+      "it": 86,
+      "life": 98,
+      "yellow": 206,
+      "bikini": 25,
+      "kayaker": 92,
+      "together": 180,
+      "scissors": 151,
+      "tennis": 175,
+      "performing": 123,
+      "stage": 165,
+      "wii": 201,
+      "striped": 168,
+      "elephant": 55,
+      "girls": 64,
+      "racket": 138
+    }
+  }
+}

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905f4141e127f6fcf1b9e7a99442195b61c263b7ddfe15847f3f51b96a4ff188
+size 59480