topics, probabilities = model.fit_transform(docs)
ConnectionError: (ProtocolError(‘Connection aborted.’, ConnectionResetError(54, ‘Connection reset by peer’)), ‘(Request ID: 5a75855f-ec0f-415b-8626-cb998e73aa80)’)
安装OpenSSL
MAC 安装
brew install OpenSSL
topics, probabilities = model.fit_transform(docs)
ConnectionError: (MaxRetryError("HTTPSConnectionPool(host=‘huggingface.co’, port=443)
topics, probabilities = model.fit_transform(docs)
conda install -c numba numba==0.56.2
遇到上面两个(4 & 5)问题基本上都是因为,默认的模型是处理英文数据,即处理word+空格的语言,对中文不适用,针对问题5:网上有个解决方案,但是我自己没有解决
最终的解决方案是不用默认的模型,换成支持中文的模型
from sentence_transformers import SentenceTransformer
embedding_model = SentenceTransformer("distiluse-base-multilingual-cased-v1")