Upload trained authorship attribution model (40 authors)

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+language:
+  - ru
+  - en
+tags:
+  - authorship-attribution
+  - stylometry
+  - text-classification
+  - scikit-learn
+---
+
+# Authorship Attribution Model
+
+Ensemble model for authorship attribution of literary texts (Russian + English).
+
+## Companion repository
+
+Source code, training pipeline, and PyQt6 desktop application:
+https://github.com/Rekname/authorship_attribution
+
+## Contents
+
+- `classifier.joblib` — trained ensemble (SVM + Random Forest + Logistic Regression)
+- `training_config.json` — training metrics and configuration
+- `sentence_transformer/` — sentence-transformer assets used by the pipeline
+
+## Dataset
+
+- 40 authors (Russian + English classical literature)
+- ~3748 chunks of 800 words each
+- 80/20 stratified train/test split, random_state=42
+
+## Usage
+
+```bash
+# Download the whole folder
+huggingface-cli download Rekname/authorship-attribution --local-dir models/
+
+# Or with git
+git clone https://huggingface.co/Rekname/authorship-attribution models/
+```
+
+Then run the desktop application from the companion repo:
+
+```bash
+git clone https://github.com/Rekname/authorship_attribution.git
+cd authorship_attribution
+uv sync
+uv run python main.py
+```
+
+## Author
+
+Малышко Александр Викторович, СДП-КБ-231, 3 курс, Кибербезопасность
+ГрГУ им. Янки Купалы, 2026

classifier.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a848a3c564dd46b8e696c898c17c7ab980ed03774b90a20dae874773e8cd3b
+size 203619325

sentence_transformer/1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

sentence_transformer/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

sentence_transformer/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

sentence_transformer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa086f0ffee582aeb45b36e34cdd1fe2d6de2bef61f8a559a1bbc9bd955917b
+size 470641600

sentence_transformer/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_transformer/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

sentence_transformer/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

sentence_transformer/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer", "tokenizer_class": "PreTrainedTokenizerFast"}

training_config.json

@@ -0,0 +1,20 @@
+{
+  "n_authors": 40,
+  "classifier_metrics": {
+    "svm": {
+      "train_accuracy": 0.9996664442961974,
+      "test_accuracy": 0.8333333333333334,
+      "display_name": "SVM"
+    },
+    "random_forest": {
+      "train_accuracy": 0.9996664442961974,
+      "test_accuracy": 0.7613333333333333,
+      "display_name": "Random Forest"
+    },
+    "logreg": {
+      "train_accuracy": 0.9996664442961974,
+      "test_accuracy": 0.8733333333333333,
+      "display_name": "Logistic Regression"
+    }
+  }
+}