SentenceTransformer加载模型的错误警告和输出精度问题

[ResDream]

Describe the bug/ 问题描述 (Mandatory / 必填)
在使用SentenceTransformer时，正确下载并加载了模型，仍然弹出警告：No sentence-transformers model found with name BAAI/bge-large-zh-v1.5. Creating a new one with MEAN pooling
与PyTorch相比输出差别有点大

• Hardware Environment(Ascend/GPU/CPU) / 硬件环境:
  ascend和CPU都存在这个问题

• Software Environment / 软件环境 (Mandatory / 必填):
  -- MindSpore version: 2.4.0和2.3.1
  -- Python version: 3.10
  -- OS platform and distribution: Linux和Windows

To Reproduce / 重现步骤 (Mandatory / 必填)

from mindnlp.sentence import SentenceTransformer
model = SentenceTransformer('BAAI/bge-large-zh-v1.5')
sentences_1 = "The weather is lovely today."
sentences_2 = "It's so sunny outside!"
embeddings_1 = model.encode(sentences_1, normalize_embeddings=True)
embeddings_2 = model.encode(sentences_2, normalize_embeddings=True)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('BAAI/bge-large-zh-v1.5')
sentences_1 = "The weather is lovely today."
sentences_2 = "It's so sunny outside!"
embeddings_1 = model.encode(sentences_1, normalize_embeddings=True)
embeddings_2 = model.encode(sentences_2, normalize_embeddings=True)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)

Expected behavior / 预期结果 (Mandatory / 必填)
A clear and concise description of what you expected to happen.

Screenshots/ 日志 / 截图 (Mandatory / 必填)
If applicable, add screenshots to help explain your problem.

Additional context / 备注 (Optional / 选填)
Add any other context about the problem here.

[lvyufeng]

fixed