Upload folder using huggingface_hub

config.json

@@ -4,6 +4,6 @@
     "AutoConfig": "configuration_sm_subgroup_classifier.SmSubgroupClassifierConfig",
     "AutoModel": "modeling_sm_subgroup_classifier.SmSubgroupClassifier"
   },
-  "available_models": ["fi_NA-nb", "fi_HI-NA-nb-re", "fi_NA-nb-OP", "NA-nb-OP-rv"],
+  "available_models": ["fi_HI-NA-nb", "fi_HI-NA-nb-re", "fi_ID", "fi_ID-NA", "fi_NA-nb", "fi_NA-nb-OP", "fi_NA-nb-OP-rv"],
   "model_type": "sm_subgroup_classifier"
 }

fi_HI-NA-nb-re/metadata.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcebec77f65e7a4edab907a0680e37b2ee48f4c384a7ff2dee7d00dc88f60749
+oid sha256:7c92e39bf82f91b113e0ac07d03c2fb9d98bb25382748bae620549beb7ee9cd9
 size 76

fi_HI-NA-nb-re/training_details.txt

@@ -3,7 +3,7 @@ Training Details for fi_HI-NA-nb-re
 
 Language: fi
 Model Name: HI-NA-nb-re
-Training Date: 2025-09-18 16:15:20
+Training Date: 2025-09-19 09:24:43
 
 Data Summary:
 - Total samples: 4597
@@ -13,8 +13,12 @@ Data Summary:
 
 Classes:
 - Number of classes: 2
-- Class names: with_comments, general
-- Class distribution: {'with_comments': 111, 'general': 4486}
+- Class names: blog_comments, general
+- Class distribution: {'blog_comments': 111, 'general': 4486}
+
+Cluster Merging:
+- 'blog_comments': kept cluster 1 (no merge)
+- 'general': kept cluster 2 (no merge)
 
 Cross-Validation Results:
 - CV folds: 5

fi_HI-NA-nb/metadata.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c569d94b6800991debcf3e841283806f74a4e5b1cda1f3eae6f37545aeb5b520
+size 71

fi_HI-NA-nb/model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a56971a10c0a58917cb4fdc08ad63020f3d3272561152f82163450a4a8d1aa
+size 9055

fi_HI-NA-nb/scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df08b921372adc99c83b8c2e724f492621a53fb05d0b75915a36f1e366c2c0e
+size 25191

fi_HI-NA-nb/training_details.txt

@@ -0,0 +1,43 @@
+Training Details for fi_HI-NA-nb
+========================================
+
+Language: fi
+Model Name: HI-NA-nb
+Training Date: 2025-09-19 09:29:41
+
+Data Summary:
+- Total samples: 934
+- Training samples: 747
+- Test samples: 187
+- Embedding dimension: 1024
+
+Classes:
+- Number of classes: 2
+- Class names: crafting, cooking
+- Class distribution: {'crafting': 521, 'cooking': 413}
+
+Cluster Merging:
+- 'crafting': kept cluster 1 (no merge)
+- 'cooking': kept cluster 2 (no merge)
+
+Cross-Validation Results:
+- CV folds: 5
+- CV scores: [0.9466666666666667, 0.9266666666666666, 0.9261744966442953, 0.9463087248322147, 0.9328859060402684]
+- CV mean: 0.9357
+- CV std: 0.0091
+- CV confidence interval: 0.9357 ± 0.0182
+
+Final Performance:
+- Test accuracy: 0.9519
+
+Model Configuration:
+- Algorithm: Logistic Regression
+- Regularization (C): 1.0
+- Feature scaling: StandardScaler
+- Random state: 42
+
+Files:
+- Classifier: model.pkl
+- Scaler: scaler.pkl
+- Metadata: metadata.pkl
+- This file: training_details.txt

fi_ID-NA/metadata.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c92e39bf82f91b113e0ac07d03c2fb9d98bb25382748bae620549beb7ee9cd9
+size 76

fi_ID-NA/model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fded060e6effa581ae765df79a6c32469fa6c8905f0ceee20781889a929d8d3f
+size 9055

fi_ID-NA/scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65976e997250b10340a77d706fde49c9d2572b62cc6ae0d2fc3101dbf449a70
+size 25191

fi_ID-NA/training_details.txt

@@ -0,0 +1,43 @@
+Training Details for fi_ID-NA
+========================================
+
+Language: fi
+Model Name: ID-NA
+Training Date: 2025-09-19 09:31:09
+
+Data Summary:
+- Total samples: 1663
+- Training samples: 1330
+- Test samples: 333
+- Embedding dimension: 1024
+
+Classes:
+- Number of classes: 2
+- Class names: blog_comments, general
+- Class distribution: {'blog_comments': 1317, 'general': 346}
+
+Cluster Merging:
+- 'blog_comments': kept cluster 1 (no merge)
+- 'general': kept cluster 2 (no merge)
+
+Cross-Validation Results:
+- CV folds: 5
+- CV scores: [0.9849624060150376, 0.9887218045112782, 0.9849624060150376, 0.9924812030075187, 0.981203007518797]
+- CV mean: 0.9865
+- CV std: 0.0038
+- CV confidence interval: 0.9865 ± 0.0077
+
+Final Performance:
+- Test accuracy: 0.9940
+
+Model Configuration:
+- Algorithm: Logistic Regression
+- Regularization (C): 1.0
+- Feature scaling: StandardScaler
+- Random state: 42
+
+Files:
+- Classifier: model.pkl
+- Scaler: scaler.pkl
+- Metadata: metadata.pkl
+- This file: training_details.txt

fi_ID/metadata.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f5f93a5f73e8dcdfa726082f2f9cbd8797e638be4d4696e7d74bfa9840f7c4
+size 76

fi_ID/model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90508b6c172f9b2ca5359037f9ce6b2ebab5c4eb62ac743449221d969984dabf
+size 9055

fi_ID/scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51544ccb9a8845358700c1923159d45551d48cf3c2ecb0146be6c42ec6042425
+size 25191

fi_ID/training_details.txt

@@ -0,0 +1,43 @@
+Training Details for fi_ID
+========================================
+
+Language: fi
+Model Name: ID
+Training Date: 2025-09-19 09:20:03
+
+Data Summary:
+- Total samples: 34973
+- Training samples: 27978
+- Test samples: 6995
+- Embedding dimension: 1024
+
+Classes:
+- Number of classes: 2
+- Class names: general, blog_comments
+- Class distribution: {'general': 32370, 'blog_comments': 2603}
+
+Cluster Merging:
+- 'general': merged clusters [np.int64(0), np.int64(2), np.int64(3)]
+- 'blog_comments': kept cluster 1 (no merge)
+
+Cross-Validation Results:
+- CV folds: 5
+- CV scores: [0.9960686204431737, 0.9958899213724088, 0.9974982130092923, 0.9935656836461126, 0.9951742627345844]
+- CV mean: 0.9956
+- CV std: 0.0013
+- CV confidence interval: 0.9956 ± 0.0026
+
+Final Performance:
+- Test accuracy: 0.9963
+
+Model Configuration:
+- Algorithm: Logistic Regression
+- Regularization (C): 1.0
+- Feature scaling: StandardScaler
+- Random state: 42
+
+Files:
+- Classifier: model.pkl
+- Scaler: scaler.pkl
+- Metadata: metadata.pkl
+- This file: training_details.txt

fi_NA-nb/metadata.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcebec77f65e7a4edab907a0680e37b2ee48f4c384a7ff2dee7d00dc88f60749
+oid sha256:7c92e39bf82f91b113e0ac07d03c2fb9d98bb25382748bae620549beb7ee9cd9
 size 76

fi_NA-nb/training_details.txt

@@ -3,7 +3,7 @@ Training Details for fi_NA-nb
 
 Language: fi
 Model Name: NA-nb
-Training Date: 2025-09-18 16:12:26
+Training Date: 2025-09-19 09:35:23
 
 Data Summary:
 - Total samples: 218088
@@ -13,8 +13,12 @@ Data Summary:
 
 Classes:
 - Number of classes: 2
-- Class names: with_comments, general
-- Class distribution: {'with_comments': 24862, 'general': 193226}
+- Class names: blog_comments, general
+- Class distribution: {'blog_comments': 24862, 'general': 193226}
+
+Cluster Merging:
+- 'blog_comments': kept cluster 1 (no merge)
+- 'general': kept cluster 2 (no merge)
 
 Cross-Validation Results:
 - CV folds: 5