Sentence Similarity
sentence-transformers
Safetensors
Persian
xlm-roberta
feature-extraction
persian
farsi
matryoshka
text-embeddings-inference
Instructions to use hanyeh00/hamsan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use hanyeh00/hamsan with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("hanyeh00/hamsan") sentences = [ "query: پایتخت ایران کجاست؟", "passage: تهران پایتخت و پرجمعیتترین شهر ایران است.", "passage: اصفهان یکی از شهرهای تاریخی ایران است.", "passage: دریای خزر بزرگترین دریاچهٔ جهان است." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from hanyeh00/hamsan: direct link, hf CLI and curl.
- Browser
- Download file 17.1 MB
-
https://huggingface.co/hanyeh00/hamsan/resolve/main/tokenizer.json
- Command line
-
hf download hf://hanyeh00/hamsan/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/hanyeh00/hamsan/resolve/main/tokenizer.json
17.1 MB
- Xet hash:
- 7f686e947e0b9d36c958512a852baddaabd2b3ff5be7abad2fb11a1fb2755fe1
- Size of remote file:
- 17.1 MB
- SHA256:
- a514807cffabd8abaf028cfaffe7ff0c4f60b97ea2db80c41f14172ae6b018ca
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.