Bilic/NeuralChat-finetuned-for-fraud-detection

This model is a fine-tuned version of Intel/neural-chat-7b-v3-1 on our custom dataset. This is a fine tuned version of the intel’s Neuralchat model, specifically trained on a carefully curated dataset on fraud detection. We implemented a contextual based architecture to enable the model learn and be adept at understanding context within a conversation as opposed to the traditional rule based approach. — detecting fraudulent conversations in real-time — Giving a summary of conversations and suggestions — Understanding with high accuracy the context in a conversation to make better predictions The following hyperparameters were used during training: — learningrate: 0.0002 — trainbatchsize: 8 — evalbatchsize: 8 — seed: 42 — optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 — lrschedulertype: cosine — trainingsteps: 250 — mixedprecisiontraining: Native AMP — Transformer

Модальности:
Генерация текста

Области применения:
Диалог / чат

Задача: Генерация текста
Автор: Bilic
Теги: tensorboard, mistral, generated_from_trainer, text-generation-inference, endpoints_compatible
Лайков: 3  |  Загрузок: 21

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.