How to use tabularisai/multilingual-emotion-classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tabularisai/multilingual-emotion-classification")
# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("tabularisai/multilingual-emotion-classification") model = AutoModelForSequenceClassification.from_pretrained("tabularisai/multilingual-emotion-classification", device_map="auto")
I'm running the model on a Mandarin dataset and the output isn't making much sense. For example, these four phrases are each >95% love:
我揍你的时候你跑比宇将军还快我两个睾丸给你伯母含我叼你姐滴b我操你妈
你去死吧 only 2% anger? 我20岁开rs4回学校的时候 班主任都想坐上我的副驾帮我口 but this is 57% anger?
· Sign up or log in to comment
