Sentence Similarity
sentence-transformers
Safetensors
Chinese
bert
feature-extraction
Generated from Trainer
dataset_size:225000
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use slxhere/modern_ancientpoem_encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use slxhere/modern_ancientpoem_encoder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("slxhere/modern_ancientpoem_encoder") sentences = [ "下班后和同事直奔常去的那家火锅店,热热闹闹地涮了一晚上。", "联延掩四远,赫弈成洪炉。", "把酒仰问天,古今谁不死。", "骑出平阳里,筵开卫尉家。" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from slxhere/modern_ancientpoem_encoder: direct link, hf CLI and curl.
- Browser
- Download file 2.61 GB
-
https://huggingface.co/slxhere/modern_ancientpoem_encoder/resolve/main/optimizer.pt
- Command line
-
hf download hf://slxhere/modern_ancientpoem_encoder/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/slxhere/modern_ancientpoem_encoder/resolve/main/optimizer.pt
2.61 GB
- Xet hash:
- 1f983de4cae932267698c5254d6aa8ee00d3ee00e62c3391c6373e59bc1f7ba2
- Size of remote file:
- 2.61 GB
- SHA256:
- cba3d24e972f7db24f5f97ae2f3dc3b3ca7310c82cca6620107eb6abc7a8c886
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.