How to use GeneZC/bert-base-stsb with Transformers:
# Load model directly from transformers import AutoTokenizer, BertCls tokenizer = AutoTokenizer.from_pretrained("GeneZC/bert-base-stsb") model = BertCls.from_pretrained("GeneZC/bert-base-stsb", device_map="auto")
bert-base-uncased finetuned on STS-b.
bert-base-uncased
STS-b
batch size is 16, learning rate is 3e-5.
pearson_corr: 0.8742, spearman_corr: 0.8707
