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

config.json

@@ -1,17 +1,16 @@
 {
-  "calculate_probabilities": false,
-  "language": "multilingual",
+  "calculate_probabilities": true,
+  "language": "english",
   "low_memory": false,
   "min_topic_size": 10,
   "n_gram_range": [
-    1,
-    1
+    2,
+    3
   ],
   "nr_topics": null,
   "seed_topic_list": null,
   "top_n_words": 10,
-  "verbose": false,
+  "verbose": true,
   "zeroshot_min_similarity": 0.7,
-  "zeroshot_topic_list": null,
-  "embedding_model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+  "zeroshot_topic_list": null
 }

ctfidf.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a226393b1e3a8e08430503e5a0761db99e6eee41ec646ad8bffd9a1adea2c44a
-size 12426256
+oid sha256:2e884c8f9e7e343ba0591480ce44ace57dbc45c5d7f57ed38ab3b052c14024ba
+size 83380832

topic_embeddings.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdd15d876c83a6abce12eb51d679f46a11b889bb2ee79cccbdf830ed88c0c443
-size 9626208
+oid sha256:d079363d27478d3373224260ec379b433ecd71a06a60f97be0091996897a269c
+size 2294880