Instructions to use leafxyz/main_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use leafxyz/main_v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("leafxyz/main_v1") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
|
Download README.md from leafxyz/main_v1: direct link, hf CLI and curl.
- Browser
- Download file 635 Bytes
-
https://huggingface.co/leafxyz/main_v1/resolve/main/README.md
- Command line
-
hf download hf://leafxyz/main_v1/README.md
-
curl -L -o README.md https://huggingface.co/leafxyz/main_v1/resolve/main/README.md
635 Bytes
metadata
language:
- ar
tags:
- dense-retrieval
- bi-encoder
- sentence-transformers
metrics:
- loss
Bi-Encoder Retrieval Model (leafxyz/main)
π Complete Training Artifacts & Logs
- Architecture: Bi-Encoder (Dense Vector Retrieval)
- Loss Function:
MultipleNegativesRankingLoss - Training Step:
500 - Training Loss:
0.177432 - Positives Loss:
0.111283 - Pairs with Negatives Loss:
0.330405
ποΈ Dataset Splits & Mixture
Data splits (Train/Validation/Test) are stored at: π leafxyz/arabic-retrieval-mixture-v2