galkinv42
/

RuModernBERT-Intent-Classifier

@@ -3,197 +3,93 @@ library_name: transformers
 tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 tags: []
 ---
+# RuModernBERT Intent Classifier
+Данная модель представляет собой классификатор интентов на базе архитектуры RuModernBERT-base, специально оптимизированный для работы в составе диалоговых голосовых систем на русском языке.
+### Описание режима
+Модель работает в режиме классификации без учета контекста. Это означает, что для предсказания намерения используется исключительно последняя реплика пользователя. Модель не требует передачи истории диалога или предыдущих ответов системы, что обеспечивает:
+* Минимальные вычислительные затраты при инференсе.
+* Возможность использования в качестве первого слоя обработки (fast-path) для определения простых команд.
+* Независимость от состояния диалога (stateless).
+---
+## Характеристики модели
+* **Базовая модель:** deepvk/RuModernBERT-base
+* **Тип задачи:** Классификация последовательностей (Multi-class Classification)
+* **Основные классы:** GREETING (приветствие), THANKS (благодарность), FAREWELL (прощание) и другие системные токены.
+* **Функция потерь:** Focal Loss (использована для коррекции дисбаланса классов в обучающей выборке).
+---
+## Инструкция по использованию (Inference)
+Для работы в режиме Regime 1 необходимо передать в модель только текст текущего сообщения пользователя.
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+import torch.nn.functional as F
+# Загрузка модели и токенизатора
+model_name = "galkinv42/RuModernBERT-Intent-Classifier"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+def predict_intent(user_input):
+    # Токенизация без добавления контекста
+    inputs = tokenizer(
+        user_input,
+        return_tensors="pt",
+        truncation=True,
+        max_length=512
+    )
+    model.eval()
+    with torch.no_grad():
+        outputs = model(**inputs)
+    # Расчет вероятностей
+    probabilities = F.softmax(outputs.logits, dim=-1)
+    confidence, class_idx = torch.max(probabilities, dim=-1)
+    label = model.config.id2label[class_idx.item()]
+    return label, confidence.item()
+# Пример вызова
+intent, score = predict_intent("Спасибо за помощь, всего доброго")
+print(f"Интент: {intent}, Уверенность: {score:.4f}")
+```
+---
+## Обучение
+1. **Данные:** Набор данных включает реальные логи диалогов, дополненные синтетическими примерами для повышения точности на минорных классах (благодарности и прощания).
+2. **Аугментация:** В процессе обучения применялась техника RandomWordAug (перестановка слов) для повышения устойчивости модели к вариативности естественной речи.
+3. **Методология:** Валидация проводилась с использованием StratifiedGroupKFold по идентификаторам диалогов, что исключает попадание фраз из одного диалога одновременно в обучающую и валидационную выборки.
+---
+## Ограничения
+* Модель не учитывает предыдущие реплики. В случаях, когда интент сильно зависит от контекста (например, краткие ответы "да", "нет", "хорошо"), точность может снижаться.
+* Предназначена исключительно для русского языка.
+---
+## Метрики
+Класс,Precision,Recall,F1-Score,Support
+<ACTION>,0.85,0.66,0.74,87
+<FAREWELL>,0.91,0.83,0.87,24
+<GREETING>,0.92,0.96,0.94,24
+<NOISE>,0.68,0.59,0.63,93
+<QUESTION>,0.85,0.91,0.88,188
+<STATEMENT>,0.62,0.74,0.67,97
+<THANKS>,1.00,0.67,0.80,3