Emotion-Aware-AI-Assistant/gemma3_4b-it-q4_K_M_discrete_results

该数据集包含多个模型的性能评估指标，主要针对情感分析任务。数据集记录了模型名称、方法、准确率、宏平均和加权平均的F1分数、精确率和召回率，以及针对愤怒、厌恶、恐惧、快乐、中性、悲伤和惊讶等特定情感的F1分数、精确率和召回率。此外，还包括混淆矩阵的JSON表示、无效计数、响应时间统计（如总时间、平均时间、标准差和众数）等信息。数据集适用于情感分析模型的性能比较和评估。

This dataset contains performance evaluation metrics for multiple models, primarily focused on emotion analysis tasks. It records model names, methods, accuracy, macro and weighted averages of F1 scores, precision and recall, as well as F1 scores, precision and recall for specific emotions such as anger, disgust, fear, happiness, neutral, sadness, and surprise. Additionally, it includes JSON representations of confusion matrices, invalid counts, response time statistics (such as total time, mean time, standard deviation, and mode), and more. The dataset is suitable for performance comparison and evaluation of emotion analysis models.