Add BERTopic model

README.md

@@ -0,0 +1,68 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# test2
+
+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("bruce-syntag/test2")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 1
+* Number of training documents: 20
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | the - and - is - to - new | 20 | -1_the_and_is_to |
+  
+</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
+
+## Framework versions
+
+* Numpy: 1.23.5
+* HDBSCAN: 0.8.33
+* UMAP: 0.5.4
+* Pandas: 1.5.3
+* Scikit-Learn: 1.2.2
+* Sentence-transformers: 2.2.2
+* Transformers: 4.35.0
+* Numba: 0.56.4
+* Plotly: 5.15.0
+* Python: 3.10.12

config.json

@@ -0,0 +1,15 @@
+{
+  "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,
+  "embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
+}

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb481126a9545eda0f7b758a118366dee989f272d6c966cffd758eb7c503faf
+size 1624

topics.json

@@ -0,0 +1,84 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "the",
+        0.18873772379335946
+      ],
+      [
+        "and",
+        0.1803097274711684
+      ],
+      [
+        "is",
+        0.09962990594386198
+      ],
+      [
+        "to",
+        0.09962990594386198
+      ],
+      [
+        "new",
+        0.08710398759233988
+      ],
+      [
+        "are",
+        0.08710398759233988
+      ],
+      [
+        "of",
+        0.07369510129820897
+      ],
+      [
+        "with",
+        0.05916812494747216
+      ],
+      [
+        "different",
+        0.04312367308066437
+      ],
+      [
+        "enjoy",
+        0.04312367308066437
+      ]
+    ]
+  },
+  "topics": [
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1
+  ],
+  "topic_sizes": {
+    "-1": 20
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_the_and_is_to"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}