Add BERTopic model

README.md

@@ -0,0 +1,72 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# BERTopic_vafn
+
+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("ychu612/BERTopic_vafn")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 3
+* Number of training documents: 103
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | the - was - she - and - to | 15 | -1_the_was_she_and | 
+| 0 | the - she - was - and - her | 55 | 0_the_she_was_and | 
+| 1 | the - was - he - and - to | 33 | 1_the_was_he_and |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: english
+* 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: 1.23.0
+* HDBSCAN: 0.8.33
+* UMAP: 0.5.5
+* Pandas: 2.1.4
+* Scikit-Learn: 1.1.0
+* Sentence-transformers: 2.3.1
+* Transformers: 4.38.1
+* Numba: 0.56.4
+* Plotly: 5.9.0
+* Python: 3.10.9

config.json

@@ -0,0 +1,17 @@
+{
+  "calculate_probabilities": false,
+  "language": "english",
+  "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,
+  "embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
+}

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadfa8aa7011577bca017f470ee45e5693f6c388f52839fd1c2fd864b7781c32
+size 4696

topics.json

@@ -0,0 +1,265 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "the",
+        0.13742718218795796
+      ],
+      [
+        "was",
+        0.10401424795221015
+      ],
+      [
+        "she",
+        0.1015715645907204
+      ],
+      [
+        "and",
+        0.07659591217201081
+      ],
+      [
+        "to",
+        0.07592298564333361
+      ],
+      [
+        "baby",
+        0.07139075689232881
+      ],
+      [
+        "her",
+        0.0629814738419722
+      ],
+      [
+        "they",
+        0.05443672238507993
+      ],
+      [
+        "that",
+        0.04770398186197523
+      ],
+      [
+        "on",
+        0.04728269721896559
+      ]
+    ],
+    "0": [
+      [
+        "the",
+        0.13844740564012709
+      ],
+      [
+        "she",
+        0.10199991617971646
+      ],
+      [
+        "was",
+        0.08782635385923653
+      ],
+      [
+        "and",
+        0.08475642666800337
+      ],
+      [
+        "her",
+        0.08108600228917424
+      ],
+      [
+        "baby",
+        0.07608382014852672
+      ],
+      [
+        "to",
+        0.07486508934251049
+      ],
+      [
+        "that",
+        0.05191060920808593
+      ],
+      [
+        "they",
+        0.0476049013649591
+      ],
+      [
+        "not",
+        0.04479719687171663
+      ]
+    ],
+    "1": [
+      [
+        "the",
+        0.14362369546548528
+      ],
+      [
+        "was",
+        0.12727289911502307
+      ],
+      [
+        "he",
+        0.07768687174821065
+      ],
+      [
+        "and",
+        0.0716539037862848
+      ],
+      [
+        "to",
+        0.07042282208672329
+      ],
+      [
+        "child",
+        0.06821516432006061
+      ],
+      [
+        "mother",
+        0.06076109057121903
+      ],
+      [
+        "she",
+        0.053563162541500516
+      ],
+      [
+        "born",
+        0.051571267513334976
+      ],
+      [
+        "baby",
+        0.05155810172983109
+      ]
+    ]
+  },
+  "topics": [
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    1,
+    1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    1,
+    1,
+    0,
+    1,
+    -1,
+    0,
+    -1,
+    0,
+    0,
+    -1,
+    -1,
+    0,
+    0,
+    -1,
+    -1,
+    0,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    1,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    0,
+    -1,
+    1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    1,
+    -1,
+    -1,
+    -1,
+    0,
+    1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    1,
+    -1,
+    1,
+    -1,
+    -1,
+    0,
+    0,
+    1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    1,
+    -1,
+    1,
+    1,
+    0,
+    0,
+    -1,
+    0,
+    -1
+  ],
+  "topic_sizes": {
+    "-1": 55,
+    "1": 15,
+    "0": 33
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ],
+    [
+      0,
+      0,
+      0
+    ],
+    [
+      1,
+      1,
+      1
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_the_was_she_and",
+    "0": "0_the_she_was_and",
+    "1": "1_the_was_he_and"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}