Add hybrid Kazakh duplicate detection model

count_vectorizer.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abc9bc7964943ee2efc8b1a78306c4e74cdf6ee474ebb39584043b3bd49cce1
+size 7938259

lda_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8197d384087679c5ad7325f9797f943567063f0ff075309cf6bb0cd0ecec0832
+size 19051589

lsa_svd.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca792e90017adb59cbadc6ee8863ab60076858dfe39c10455f8d6ddd5645976c
+size 245972743

meta.json

@@ -0,0 +1,22 @@
+{
+  "created_at": "2026-02-10T06:39:36.939185",
+  "dataset": "Arailym-tleubayeva/KazakhTextDuplicates",
+  "preprocessing": {
+    "ngram_n": 3,
+    "stopwords_count": 135
+  },
+  "lsa": {
+    "n_components": 100
+  },
+  "lda": {
+    "n_topics": 10
+  },
+  "fusion": {
+    "weights": {
+      "jaccard": 0.3,
+      "lsa": 0.4,
+      "lda": 0.3
+    },
+    "threshold": 0.7
+  }
+}

tfidf_vectorizer.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179f9c8cad3b88ab354b2be1aabf3906e67a9697b42108175f913dca73c50f87
+size 10398320