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 +1,149 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# BERTopic_6_months
+
+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("karinegabsschon/BERTopic_6_months")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 80
+* Number of training documents: 5537
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | electric - vehicles - car - cars - ev | 21 | electric cars | electric vehicles | electric car | 
+| 0 | grant - scheme - car grant - government - 750 | 1297 | electric vehicles | electric cars | electric car | 
+| 1 | charging - chargers - public - ev - drivers | 216 | ev charging | charging infrastructure | ev chargers | 
+| 2 | tesla - musk - model - company - elon | 215 | tesla shares | tesla sales | tesla nasdaq | 
+| 3 | uk - government - zero - mandate - targets | 153 | diesel cars | electric cars | electric vehicles | 
+| 4 | tesla - sales - musk - tesla sales - year | 113 | tesla sales | tesla market | year tesla | 
+| 5 | kia - range - car - hyundai - electric | 108 | kia ev9 | ev | kia | 
+| 6 | xiaomi - yu7 - su7 - china - chinese | 107 | xiaomi yu7 | xiaomi electric | xiaomi su7 | 
+| 7 | tax - car tax - car - rates - pay | 106 | car tax | electric vehicles | electric car | 
+| 8 | tax - spd - purchase - coalition - funding | 104 | purchase incentives | purchase premium | purchase premiums | 
+| 9 | charging - energy - solutions - ev charging - ev | 98 | ev charging | ev charger | charging infrastructure | 
+| 10 | charging - romania - abstract - electric - charging points | 98 | ev charging | charging infrastructure | charging points | 
+| 11 | toyota - honda - subaru - japanese - nissan | 96 | electric vehicles | electric cars | electric car | 
+| 12 | battery - batteries - catl - lithium - solid | 89 | ev battery | ev batteries | battery technology | 
+| 13 | byd - charging - minutes - fast - han | 85 | megawatt charging | fast charging | charging times | 
+| 14 | charging - stations - charging stations - charging points - points | 84 | charging infrastructure | charging cars | charging stations | 
+| 15 | fires - battery - safety - police - car | 83 | ev fires | battery fires | car fires | 
+| 16 | byd - tesla - sales - chinese - year | 80 | tesla sales | overtakes tesla | tesla | 
+| 17 | ford - farley - company - platform - kentucky | 78 | ford ceo | ford | ford motor | 
+| 18 | india - indian - ev - tata - mobility | 75 | tata motors | tesla | tata | 
+| 19 | ukraine - units - used - region - kyiv | 72 | vehicles ukraine | electric vehicles | electric cars | 
+| 20 | percent - cars - registrations - germany - registered | 66 | electric cars | cars germany | registered cars | 
+| 21 | vinfast - vf - vietnam - green - philippines | 63 | vinfast auto | vinfast vf | vehicle ev | 
+| 22 | used - used car - used electric - percent - battery | 62 | electric cars | electric vehicles | car market | 
+| 23 | new - registrations - new car - sales - year | 59 | ev sales | electric cars | electric car | 
+| 24 | id - volkswagen - every1 - vw - id every1 | 58 | volkswagen id | electric car | vw wants | 
+| 25 | mercedes - cla - new - range - eqs | 56 | mercedes cla | cla ev | new mercedes | 
+| 26 | emissions - electricity - study - cars - combustion | 53 | electric cars | electric car | electric vehicles | 
+| 27 | tariffs - eu - china - mexico - trade | 51 | tariffs chinese | car tariffs | additional tariffs | 
+| 28 | car - charge - miles - ve - trip | 51 | electric car | electric cars | ev | 
+| 29 | byd - chinese - price war - price - war | 49 | chinese car | china electric | chinese electric | 
+| 30 | rivian - r2 - nasdaq - rivn - scaringe | 48 | rivian automotive | ev stocks | rivian | 
+| 31 | charging - stations - charging stations - terminals - station | 47 | charging stations | electric vehicles | electric car | 
+| 32 | percent - registrations - eu - cars - year | 46 | electric cars | electric vehicles | european car | 
+| 33 | licensed - cars licensed - czech - czech republic - republic | 44 | electric cars | electric vehicles | cars licensed | 
+| 34 | hungary - byd - huf - chinese - serbia | 41 | chinese electric | china xplained | hungary | 
+| 35 | moves - aid - moves iii - iii - euros | 40 | electric vehicles | electric vehicle | electric car | 
+| 36 | china - shanghai - chinese - market - car | 40 | chinese automotive | shanghai auto | china auto | 
+| 37 | stellantis - ferrari - fiat - lamborghini - italian | 40 | electric car | 500 hybrid | electric vehicle | 
+| 38 | indonesia - lg - alpine - battery - ev battery | 39 | indonesia battery | indonesia ev | ev battery | 
+| 39 | tesla - musk - black - elon - tsla | 39 | tesla | tesla nasdaq | elon musk | 
+| 40 | foxconn - mitsubishi - nissan - japanese - mitsubishi motors | 39 | japanese automaker | taiwanese electronics | taiwan foxconn | 
+| 41 | credit - tax - trump - tax credit - states | 38 | electric vehicle | electric vehicles | vehicle credit | 
+| 42 | storage - electricity - energy - batteries - grid | 38 | energy storage | ev batteries | battery storage | 
+| 43 | european - commission - eu - industry - emissions | 37 | european automotive | european car | electric vehicles | 
+| 44 | dolphin - surf - dolphin surf - byd - euros | 37 | dolphin surf | byd dolphin | dolphin | 
+| 45 | german - vw - place - market - brands | 37 | german car | vw dominates | bmw | 
+| 46 | russia - russian - stations - electric - moscow | 37 | russia electric | russian electric | electric cars | 
+| 47 | slate - truck - northvolt - bezos - slate auto | 36 | slate truck | electric vehicle | tesla | 
+| 48 | audi - porsche - döllner - cellforce - tt | 36 | audi | audi tt | audi ceo | 
+| 49 | bonus - euros - ecological - aid - energy | 36 | purchase electric | electric car | electric vehicles | 
+| 50 | percent - cars - city - registered - vienna | 35 | electric cars | new cars | electric mobility | 
+| 51 | used - value - cent - used car - prices | 34 | ev values | electric cars | electric vehicles | 
+| 52 | points - spain - charging points - charging - indicator | 33 | charging infrastructure | charging points | charging network | 
+| 53 | gm - general motors - general - motors - equinox | 33 | ev gm | gm electric | chevrolet equinox | 
+| 54 | million - sales - china - global - electric | 33 | ev market | electric cars | electric car | 
+| 55 | nio - firefly - onvo - chinese - li | 31 | nio tesla | tesla chinese | tesla | 
+| 56 | california - trump - federal - states - vehicle | 31 | california electric | electric vehicles | electric vehicle | 
+| 57 | lucid - nikola - lcid - uber - nasdaq | 30 | lucid shares | vehicles lucid | nasdaq lcid | 
+| 58 | breakdown - barriers - cent - adac - breakdowns | 30 | electric cars | electric vehicles | engine vehicles | 
+| 59 | nissan - leaf - micra - generation - new | 29 | nissan leaf | generation nissan | electric car | 
+| 60 | uzbekistan - kazakhstan - proton - stations - tashkent | 28 | uzbekistan | tashkent region | electric vehicles | 
+| 61 | range - kilometers - test - km - real | 28 | electric car | electric cars | efficient electric | 
+| 62 | french - france - electric - centrale - la centrale | 27 | electric cars | electric car | french car | 
+| 63 | xpeng - p7 - ai - g6 - chinese | 27 | xpeng g6 | xpeng p7 | xpeng x9 | 
+| 64 | belarus - belgee - charging - belorusneft - stations | 26 | belarus electric | vehicles belarus | infrastructure belarus | 
+| 65 | volkswagen - group - vw - europe - deliveries | 26 | germany volkswagen | volkswagen | volkswagen group | 
+| 66 | tesla - musk - protests - elon - elon musk | 26 | tesla takedown | tesla electric | tesla cybertruck | 
+| 67 | pod - pod point - edf - point - owen | 26 | pod point | ev charging | pod drive | 
+| 68 | combustion - price - discounts - gap - dudenhöffer | 26 | electric cars | price gap | electric car | 
+| 69 | cost - costs - charge - price cap - cap | 25 | charge ev | energy price | electric car | 
+| 70 | recycling - batteries - battery - battery recycling - lithium | 25 | battery recycling | ev batteries | ev battery | 
+| 71 | record - kilometers - lucid - amg - mercedes | 25 | electric car | longest distance | car travels | 
+| 72 | leapmotor - c10 - stellantis - t03 - grant | 25 | leapmotor uk | leapmotor vehicles | leapmotor electric | 
+| 73 | percent - survey - respondents - car - cars | 24 | electric car | electric cars | buy electric | 
+| 74 | renault - r5 - twingo - r4 - car | 24 | renault r5 | electric car | new renault | 
+| 75 | musk - trump - elon - elon musk - president | 23 | tesla | trump musk | elon musk | 
+| 76 | mg - s5 - mg4 - cyberster - s5 ev | 22 | mgs5 ev | s5 ev | mg s5 | 
+| 77 | spain - units - year - electrified - month | 22 | electric cars | cars spain | sales electric | 
+| 78 | london - congestion - congestion charge - tfl - charge | 22 | exemption evs | london congestion | congestion charge |
+
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* 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: 0.5.9.post2
+* Pandas: 2.2.2
+* Scikit-Learn: 1.6.1
+* Sentence-transformers: 5.1.0
+* Transformers: 4.55.4
+* Numba: 0.60.0
+* Plotly: 5.24.1
+* Python: 3.12.11

config.json

@@ -0,0 +1,17 @@
+{
+  "calculate_probabilities": false,
+  "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,
+  "embedding_model": "ibm-granite/granite-embedding-125m-english"
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89524b23f41fb41a014b29da4bff19c1b9c53a77fcd41719f6999c2ca6c96181
+size 16170388

ctfidf_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9f3740c3ba8dcf8e59920473990450cc68bfa30181c06a87fe81f6b531bab5
+size 18773339

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd0bc860513f52059d03d935ec0eea82e79e17b62f2a81ac916b284f69d67c08
+size 245848