Upload folder using huggingface_hub

README.md

@@ -1,3 +1,30 @@
----
-license: mit
----
+# spam-classifier-ru 🛡️
+
+Модель `spam-classifier-ru` предназначена для бинарной классификации текстов на русском языке (Спам / Не спам). 
+
+Модель представляет собой fine-tuned версию архитектуры `cointegrated/rubert-tiny2`.
+
+## 📚 Данные для обучения (Training Data)
+В качестве основы использовалась подвыборка в размере 500 000 строк из открытого датасета [ruSpamModels/russian-spam-detection](https://huggingface.co/datasets/ruSpamModels/russian-spam-detection). 
+
+## Пример использования
+
+```python 
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+model_name = "твой_ник/spam-classifier-ru"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+text = "3APA60T0K 6E3 BЛ0ЖEHИЙ 0T 5OOO PY6ЛEЙ B ДEHb!"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
+
+with torch.no_grad():
+    outputs = model(**inputs)
+
+predicted_class = torch.argmax(outputs.logits, dim=-1).item()
+
+print("Это спам!" if predicted_class == 1 else "Это нормальный текст.")
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "emb_size": 312,
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 83828
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8479afbc1130695e5f64406ad00c11322d8dac16b653460718195cbfcbde74
+size 116784136

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9c17e6009e7c10b082089f2b68a1ce60441bbb251de76c0d81d0f68812f32e
+size 5265