Add BERTopic model

README.md

@@ -0,0 +1,74 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# rag-topic-model
+
+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("ivanleomk/rag-topic-model")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 5
+* Number of training documents: 243
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | the - verification - my - for - code | 24 | -1_the_verification_my_for | 
+| 0 | klarna - to - my - and - the | 19 | 0_klarna_to_my_and | 
+| 1 | my - the - return - store - still | 98 | 1_my_the_return_store | 
+| 2 | card - onetime - my - it - for | 69 | 2_card_onetime_my_it | 
+| 3 | payment - my - due - date - the | 33 | 3_payment_my_due_date |
+  
+</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: False
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 2.0.2
+* HDBSCAN: 0.8.40
+* UMAP: 0.5.7
+* Pandas: 2.2.3
+* Scikit-Learn: 1.5.2
+* Sentence-transformers: 3.3.1
+* Transformers: 4.46.3
+* Numba: 0.60.0
+* Plotly: 5.24.1
+* Python: 3.9.6

config.json

@@ -0,0 +1,16 @@
+{
+  "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": false,
+  "zeroshot_min_similarity": 0.7,
+  "zeroshot_topic_list": null
+}

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1384d89ba5fb76e29d40fbf2f181cc734803e4f0132a177597658df4740d522
+size 7768

topics.json

@@ -0,0 +1,503 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "the",
+        0.09492240491569903
+      ],
+      [
+        "verification",
+        0.06970153771334807
+      ],
+      [
+        "my",
+        0.06435254147435229
+      ],
+      [
+        "for",
+        0.06319899047478812
+      ],
+      [
+        "code",
+        0.057297419223293365
+      ],
+      [
+        "whats",
+        0.05231884901424003
+      ],
+      [
+        "step",
+        0.05048680075415213
+      ],
+      [
+        "email",
+        0.04766755006544382
+      ],
+      [
+        "to",
+        0.04691532073995217
+      ],
+      [
+        "up",
+        0.046032377461675815
+      ]
+    ],
+    "0": [
+      [
+        "klarna",
+        0.09050803422673742
+      ],
+      [
+        "to",
+        0.07953560782302285
+      ],
+      [
+        "my",
+        0.06794819842776671
+      ],
+      [
+        "and",
+        0.054212681447924974
+      ],
+      [
+        "the",
+        0.05221408034992652
+      ],
+      [
+        "for",
+        0.04986631308226638
+      ],
+      [
+        "im",
+        0.046128149776214315
+      ],
+      [
+        "but",
+        0.04290244254915681
+      ],
+      [
+        "card",
+        0.038263701287704434
+      ],
+      [
+        "with",
+        0.03806685276761612
+      ]
+    ],
+    "1": [
+      [
+        "my",
+        0.0775192391698972
+      ],
+      [
+        "the",
+        0.07083659770502172
+      ],
+      [
+        "return",
+        0.06282550489124095
+      ],
+      [
+        "store",
+        0.06030699514817177
+      ],
+      [
+        "still",
+        0.05232050981790259
+      ],
+      [
+        "and",
+        0.048850488312254275
+      ],
+      [
+        "to",
+        0.04440410670920632
+      ],
+      [
+        "but",
+        0.04435407181783497
+      ],
+      [
+        "weeks",
+        0.04390700519309823
+      ],
+      [
+        "refund",
+        0.04301759717367365
+      ]
+    ],
+    "2": [
+      [
+        "card",
+        0.15173156476046484
+      ],
+      [
+        "onetime",
+        0.09616516102360437
+      ],
+      [
+        "my",
+        0.06662856796086986
+      ],
+      [
+        "it",
+        0.06433874526122811
+      ],
+      [
+        "for",
+        0.062288342197053426
+      ],
+      [
+        "but",
+        0.05809184320425647
+      ],
+      [
+        "to",
+        0.049909093780171436
+      ],
+      [
+        "and",
+        0.04702598592456893
+      ],
+      [
+        "is",
+        0.04567791318517409
+      ],
+      [
+        "the",
+        0.044549831866569335
+      ]
+    ],
+    "3": [
+      [
+        "payment",
+        0.12112085020085236
+      ],
+      [
+        "my",
+        0.0998606282868899
+      ],
+      [
+        "due",
+        0.09304345529961551
+      ],
+      [
+        "date",
+        0.08822107880850269
+      ],
+      [
+        "the",
+        0.07715617939671793
+      ],
+      [
+        "is",
+        0.06934959789854092
+      ],
+      [
+        "cant",
+        0.06277156684324331
+      ],
+      [
+        "plan",
+        0.06161981560504852
+      ],
+      [
+        "than",
+        0.04929585248403881
+      ],
+      [
+        "an",
+        0.04763634941129883
+      ]
+    ]
+  },
+  "topics": [
+    0,
+    3,
+    0,
+    0,
+    0,
+    1,
+    1,
+    0,
+    3,
+    0,
+    2,
+    0,
+    1,
+    3,
+    2,
+    0,
+    1,
+    0,
+    1,
+    0,
+    1,
+    1,
+    0,
+    0,
+    1,
+    0,
+    2,
+    3,
+    3,
+    1,
+    0,
+    0,
+    0,
+    1,
+    3,
+    3,
+    1,
+    1,
+    0,
+    0,
+    1,
+    0,
+    1,
+    0,
+    0,
+    3,
+    3,
+    1,
+    2,
+    0,
+    1,
+    0,
+    0,
+    0,
+    1,
+    1,
+    -1,
+    3,
+    3,
+    1,
+    2,
+    0,
+    2,
+    2,
+    2,
+    0,
+    1,
+    2,
+    1,
+    1,
+    0,
+    0,
+    3,
+    1,
+    2,
+    3,
+    1,
+    0,
+    0,
+    0,
+    3,
+    0,
+    2,
+    3,
+    1,
+    0,
+    1,
+    1,
+    0,
+    0,
+    1,
+    -1,
+    0,
+    3,
+    2,
+    0,
+    2,
+    1,
+    -1,
+    -1,
+    0,
+    1,
+    0,
+    1,
+    -1,
+    0,
+    2,
+    3,
+    0,
+    3,
+    1,
+    1,
+    0,
+    0,
+    3,
+    3,
+    1,
+    1,
+    3,
+    3,
+    1,
+    0,
+    0,
+    3,
+    0,
+    1,
+    3,
+    1,
+    1,
+    0,
+    0,
+    0,
+    0,
+    1,
+    0,
+    0,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    0,
+    0,
+    2,
+    0,
+    1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    2,
+    1,
+    0,
+    0,
+    0,
+    -1,
+    0,
+    0,
+    -1,
+    0,
+    1,
+    -1,
+    2,
+    2,
+    2,
+    1,
+    1,
+    1,
+    2,
+    0,
+    0,
+    2,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    2,
+    1,
+    1,
+    2,
+    -1,
+    2,
+    1,
+    1,
+    2,
+    2,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    2,
+    1,
+    -1,
+    1,
+    1,
+    2,
+    1,
+    1,
+    1,
+    1,
+    0,
+    0,
+    -1,
+    0,
+    -1,
+    1,
+    1,
+    2,
+    0,
+    0,
+    0,
+    1,
+    0,
+    0,
+    0,
+    1,
+    2,
+    2,
+    1,
+    2,
+    -1,
+    -1,
+    1,
+    -1,
+    2,
+    0,
+    0
+  ],
+  "topic_sizes": {
+    "0": 98,
+    "3": 24,
+    "1": 69,
+    "2": 33,
+    "-1": 19
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ],
+    [
+      0,
+      0,
+      3
+    ],
+    [
+      1,
+      1,
+      0
+    ],
+    [
+      2,
+      2,
+      2
+    ],
+    [
+      3,
+      3,
+      1
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_the_verification_my_for",
+    "0": "0_klarna_to_my_and",
+    "1": "1_my_the_return_store",
+    "2": "2_card_onetime_my_it",
+    "3": "3_payment_my_due_date"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}