C2 Roberta Base Finetuned Dianping Chinese

🚀 liam168/c2-roberta-base-finetuned-dianping-chinese

A model trained on Chinese dialogue sentiment corpus for binary classification: optimistic and pessimistic.

🚀 Quick Start

This model is trained with Chinese dialogue sentiment corpus and is used for binary classification of sentiment, distinguishing between optimistic and pessimistic emotions.

✨ Features

• Language model: BertForSequenceClassification
• Model size: 410M
• Language: Chinese

💻 Usage Examples

Basic Usage

>>> from transformers import AutoModelForSequenceClassification , AutoTokenizer, pipeline

>>> model_name = "liam168/c2-roberta-base-finetuned-dianping-chinese"
>>> class_num = 2
>>> ts_texts = ["我喜欢下雨。", "我讨厌他."]
>>> model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=class_num)
>>> tokenizer = AutoTokenizer.from_pretrained(model_name)
>>> classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
>>> classifier(ts_texts[0])
>>> classifier(ts_texts[1])

[{'label': 'positive', 'score': 0.9973447918891907}]
[{'label': 'negative', 'score': 0.9972558617591858}]