CrossEncoder based on BAAI/bge-reranker-v2-m3

This is a Cross Encoder model finetuned from BAAI/bge-reranker-v2-m3 using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

  • Model Type: Cross Encoder
  • Base model: BAAI/bge-reranker-v2-m3
  • Maximum Sequence Length: 8192 tokens
  • Number of Output Labels: 1 label

Model Sources

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import CrossEncoder

# Download from the ๐Ÿค— Hub
model = CrossEncoder("guyhadad01/cross")
# Get scores for pairs of texts
pairs = [
    ['query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”', 'passage: ืžื“ืจื™ืš ืœืงื‘ืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื’ื•ื‘ื” ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ืกื›ื•ืžื™ื ืฉืœื ื ืœืงื—ื™ื ื‘ื—ืฉื‘ื•ืŸ ืœืฆื•ืจืš ื—ื™ืฉื•ื‘ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืขืœ ืžื‘ืงืฉ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœื“ื•ื•ื— ืขืœ ื”ื›ื ืกื•ืชื™ื• ื›ื“ื™ ืœื‘ื“ื•ืง ื–ื›ืื•ืช ืœืงื‘ืœื” ื•ืœื—ืฉื‘ ืืช ืฉื•ื•ื™ื”. ืขื ื–ืืช, ื”ื”ื›ื ืกื•ืช ื”ื‘ืื•ืช ืœื ื ื›ืœืœื•ืช ื‘ื—ื™ืฉื•ื‘ ื–ื”: ืงืฆื‘ืช ื™ืœื“ื™ื ื’ืžืœืช ื™ืœื“ ื ื›ื” ืงืฆื‘ืช ืฉื™ืจื•ืชื™ื ืžื™ื•ื—ื“ื™ื ื’ืžืœืช ื ื™ื™ื“ื•ืช ื’ืžืœืช ืกื™ืขื•ื“ ื“ืžื™ ืžื—ื™ื” ืœืืœืžื ื” ื•ืœื™ืชื•ื ืงืฆื‘ืื•ืช ืžื™ื•ื—ื“ื•ืช ืœื ื›ื™ ืขื‘ื•ื“ื” ืงืฆื‘ื” ืื• ื”ื˜ื‘ื” ื”ืžืฉื•ืœืžืช ืœื ื–ืงืงื™ื ืขืœ ืคื™ ื—ื•ืง ืฉื™ืจื•ืชื™ ื”ืกืขื“ ืชืฉืœื•ืžื™ื ืฉื”ืงื•ื ื’ืจืก ื”ื™ื”ื•ื“ื™ ื”ืขื•ืœืžื™ ืžืฉืœื ืœื—ืกื™ื“ื™ ืื•ืžื•ืช ื”ืขื•ืœื ืชืžื™ื›ื” ื›ืกืคื™ืช ื”ื ื™ืชื ืช ื›ืกื™ื•ืข ื‘ืชืฉืœื•ื ืฉื›ืจ ื“ื™ืจื” ืœืžื™ ืฉืžืฉื›ื™ืจ ืืช ื“ื™ืจืชื• ื•ืฉื•ื›ืจ ื“ื™ืจื” ืื—ืจืช ืœืžื’ื•ืจื™ื•, ืœื ืชื™ืœืงื— ื‘ื—ืฉื‘ื•ืŸ ื”ื”ื›ื ืกื” ืžื”ืฉื›ืจืช ื“ื™ืจืชื• ืฉืื™ื ื” ืขื•ืœื” ืขืœ ืกื›ื•ื ื“ืžื™ ื”ืฉื›ื™ืจื•ืช ืฉื”ื•ื ืžืฉืœื (ื”ื—ืœ ืžื”-01.01.2019) ืชืฉืœื•ืžื™ ืžื–ื•ื ื•ืช ืœืื™ืฉื” ืื• ืœื™ืœื“ื™ื, ื›ืœ ืขื•ื“ ื”ื ืœื ืขื•ืœื™ื ืขืœ ืกื›ื•ื ืงืฆื‘ืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื”ืžื’ื™ืขื” ืœื•. ืื ืื“ื ื ืชืžืš ื›ืกืคื™ืช ื‘ืื•ืคืŸ ืงื‘ื•ืข ื•ืœืœื ืชืžื•ืจื” ืžื‘ื ื™ ืžืฉืคื—ื” ืื• ืžื’ื•ืจื ื‘ืงื”ื™ืœื” ื›ื’ื•ืŸ ืขืžื•ืชื”, ื”ืกื›ื•ื ืœื ื™ื—ืฉื‘ ื›ื”ื›ื ืกื” ืœืฆื•ืจืš ื”ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ืขื ื–ืืช, ืกื›ื•ืžื™ ืชืžื™ื›ื” ื’ื‘ื•ื”ื™ื ื‘ืื•ืคืŸ ื—ืจื™ื’ ืขืœื•ืœื™ื ืœืคื’ื•ืข ื‘ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ืชืฉืœื•ืžื™ื ืฉื”ื—ื•ืง ืœื ืงื•ื‘ืข ืœื’ื‘ื™ื”ื ื‘ืžืคื•ืจืฉ ื›ื™ ื”ื ืื™ื ื ื ื—ืฉื‘ื™ื ืœื”ื›ื ืกื”, ื™ื•ื‘ืื• ื‘ื—ืฉื‘ื•ืŸ ื‘ืžืกื’ืจืช ืžื‘ื—ืŸ ื”ื”ื›ื ืกื•ืช. ื›ืžื• ื›ืŸ, ื™ืฉื ื ืžืขื ืงื™ื ืฉื ืงื‘ืข ื‘ืžืคื•ืจืฉ ื‘ื—ื•ืง ื›ื™ ื”ื ื™ื™ื—ืฉื‘ื• ื›ื”ื›ื ืกื”. ืœืžื™ื“ืข ื ื•ืกืฃ ืจืื•: ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ("ื”ื›ื ืกื•ืช ื•ื ื›ืกื™ื")'],
    ['query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”', 'passage: ืžื“ืจื™ืš ืœืงื‘ืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื’ื•ื‘ื” ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื’ื•ืจืžื™ื ืฉื ืœืงื—ื™ื ื‘ื—ืฉื‘ื•ืŸ ืœืฆื•ืจืš ื—ื™ืฉื•ื‘ ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื‘ืขืช ื‘ืงืฉืช ื”ื”ื‘ื˜ื—ื” ื™ืฉ ืœื“ื•ื•ื— ืขืœ ื”ื”ื›ื ืกื•ืช ื•ื”ื ื›ืกื™ื ื”ื‘ืื™ื: ื”ื›ื ืกื•ืช ืžืขื‘ื•ื“ื” ืฉื•ื•ื™ ืจื›ื‘ ื ื›ืกื™ื ืคื™ื ื ืกื™ื™ื ื›ื’ื•ืŸ ื—ืกื›ื•ื ื•ืช ื•ืคืง"ืž. ืฉื•ื•ื™ ืขืจืš ื ื“ืœ"ืŸ ื›ืคื™ ืฉื™ื™ืงื‘ืข ืขืœ ื™ื“ื™ ืฉืžืื™ ืžื•ืกืžืš ืžื˜ืขื ื”ืžื•ืกื“ ืœื‘ื™ื˜ื•ื— ืœืื•ืžื™ ื•ื‘ื”ืชืื ืœืžืฆื‘ ื”ืžืฉืคื—ืชื™, ืžืกืคืจ ื”ื™ืœื“ื™ื ื•ื’ื™ืœ ืžื‘ืงืฉ ื”ื’ืžืœื”. ืœืžื™ื“ืข ื ื•ืกืฃ ืจืื•: ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ("ื”ื›ื ืกื•ืช ื•ื ื›ืกื™ื") ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื•ื‘ืขืœื•ืช ืขืœ ืจื›ื‘'],
    ['query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”', 'passage: ื”ื’ื‘ืœืช ืฉื›ืจ ื˜ืจื—ื” ืขื‘ื•ืจ ืกื™ื•ืข ืื• ื™ื™ืฆื•ื’ ื‘ืชื‘ื™ืขื” ืœืงืฆื‘ืช ื ื›ื•ืช ื•ืžืขื ืง ื ื›ื•ืช ืœื ืคื’ืขื™ ืขื‘ื•ื“ื” ื—ื™ืฉื•ื‘ ืฉื›ืจ ื”ื˜ืจื—ื” ื‘ืžืงืจื™ื ื‘ื”ื ื”ืชื•ื‘ืข ืงื™ื‘ืœ ื’ืžืœื” ืœืคื ื™ ืฉื”ื’ื™ืฉ ืืช ื”ืชื‘ื™ืขื” ื›ืืฉืจ ื”ืชื•ื‘ืข ืงื™ื‘ืœ ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื•ื›ืชื•ืฆืื” ืžื”ืชื‘ื™ืขื” ื”ื•ื ืžืงื‘ืœ ืงืฆื‘ืช ื ื›ื•ืช ืœื ืคื’ืขื™ ืขื‘ื•ื“ื” ื‘ื ื•ืกืฃ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ืœืฉื›ืจ ื”ื˜ืจื—ื” ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,800 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืขื‘ื•ื“ื”, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ื” ื‘ืกืš 2,400 โ‚ช. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” 907 โ‚ช ื•-17% ืžื”ืงืฆื‘ื” ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื (ืจืื• ื˜ื‘ืœื” ืœืขื™ืœ). ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ื•ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื”ื•ืคืกืงื” ื‘ืขืงื‘ื•ืช ืงื‘ื™ืขืช ื”ื–ื›ืื•ืช ืœืงืฆื‘ืช ื”ื ื›ื•ืช, ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื—ื•ืฉื‘ ืขืœ ืคื™ ื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช, ื•ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,400 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืขื‘ื•ื“ื”, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ืช ื ื›ื•ืช ื‘ืกืš 3,800 โ‚ช. ื‘ืขืงื‘ื•ืช ืงื‘ืœืช ืงืฆื‘ืช ื”ื ื›ื•ืช, ื ืžืฆื ืฉื”ืชื•ื‘ืข ื›ื‘ืจ ืื™ื ื• ื–ื›ืื™ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ืฉืงื™ื‘ืœ, ื•ื–ื• ื”ื•ืคืกืงื”. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” ืกื›ื•ื ื”ื™ืกื•ื“ ื‘ืกืš 907 โ‚ช ื•-17% ืžื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช (17% ืž-2,400 โ‚ช, ืฉื”ื 408 โ‚ช) ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื.'],
    ['query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”', 'passage: ื”ื’ื‘ืœืช ืฉื›ืจ ื˜ืจื—ื” ืขื‘ื•ืจ ืกื™ื•ืข ืื• ื™ื™ืฆื•ื’ ื‘ืชื‘ื™ืขื” ืœื’ืžืœืช ื ื›ื•ืช ืžืชื ื“ื‘ื™ื ื—ื™ืฉื•ื‘ ืฉื›ืจ ื”ื˜ืจื—ื” ื‘ืžืงืจื™ื ื‘ื”ื ื”ืชื•ื‘ืข ืงื™ื‘ืœ ื’ืžืœื” ืœืคื ื™ ืฉื”ื’ื™ืฉ ืืช ื”ืชื‘ื™ืขื” ืชื•ื‘ืข ืฉืงื™ื‘ืœ ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื•ื›ืชื•ืฆืื” ืžื”ืชื‘ื™ืขื” ื”ื•ื ืžืงื‘ืœ ืงืฆื‘ืช ื ื›ื•ืช ื‘ื ื•ืกืฃ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ืœืฉื›ืจ ื”ื˜ืจื—ื” ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,800 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืชื ื“ื‘ื™ื, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ื” ื‘ืกืš 2,400 โ‚ช. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” 907 โ‚ช ื•-17% ืžื”ืงืฆื‘ื” ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื (ืจืื• ื˜ื‘ืœื” ืœืขื™ืœ). ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ื•ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื”ื•ืคืกืงื” ื‘ืขืงื‘ื•ืช ืงื‘ื™ืขืช ื”ื–ื›ืื•ืช ืœืงืฆื‘ืช ื”ื ื›ื•ืช, ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื—ื•ืฉื‘ ืขืœ-ืคื™ ื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช, ื•ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,400 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืชื ื“ื‘ื™ื, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ืช ื ื›ื•ืช ื‘ืกืš 3,800 โ‚ช. ื‘ืขืงื‘ื•ืช ืงื‘ืœืช ืงืฆื‘ืช ื”ื ื›ื•ืช, ื ืžืฆื ืฉื”ืชื•ื‘ืข ื›ื‘ืจ ืื™ื ื• ื–ื›ืื™ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ืฉืงื™ื‘ืœ, ื•ื–ื• ื”ื•ืคืกืงื”. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” 907 โ‚ช ื•-17% ืžื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช (17% ืž-2,400 โ‚ช, ืฉื”ื 408 โ‚ช) ื‘ื›ืœ ื—ื•ื“ืฉ, ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื.'],
    ['query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”', 'passage: ืžื“ืจื™ืš ืœืงื‘ืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืื• ื”ืฉืœืžืช ื”ื›ื ืกื” ืžื™ ืฉืขื•ืžื“ ื‘ืชื ืื™ ื”ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ื™ื›ื•ืœ ืœื”ื™ื•ืช ื–ื›ืื™ ืœื’ืžืœื” ืžืœืื”, ืื• ืœื’ืžืœื” ื—ืœืงื™ืช ื”ื™ื“ื•ืขื” ื’ื ื‘ืฉื "ื”ืฉืœืžืช ื”ื›ื ืกื”". ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืžืชืงื™ื™ืžืช ืื ืžืชืงื™ื™ืžื™ื 3 ืชื ืื™ื ืžืฆื˜ื‘ืจื™ื: ืชื•ืฉื‘ื•ืช ื‘ื™ืฉืจืืœ ืœืžืฉืš 24 ื—ื•ื“ืฉื™ื ืจืฆื•ืคื™ื, ืœืžืขื˜ ื‘ืžืงืจื™ื ืžื™ื•ื—ื“ื™ื. ื’ื™ืœ ื”ืžื‘ืงืฉ ืžืขืœ 20, ืœืžืขื˜ ื‘ืžืงืจื™ื ืžื™ื•ื—ื“ื™ื. ื”ืžื‘ืงืฉ ืจืฉื•ื ื‘ืœืฉื›ืช ื”ืชืขืกื•ืงื” ืื• ืžืชื™ื™ืฆื‘ ื‘ื” ื‘ื”ืชืื ืœื”ื ื—ื™ื•ืชื™ื”, ื‘ืฉืœ ืื—ืช ืžื”ืกื™ื‘ื•ืช ื”ื‘ืื•ืช: ื”ื•ื ืžื—ื•ืกืจ ืขื‘ื•ื“ื” ื•ืœืฉื›ืช ื”ืชืขืกื•ืงื” ื˜ืจื ื”ืฆื™ืขื” ืœื• ืขื‘ื•ื“ื” ื”ืชื•ืืžืช ืืช ืžืฆื‘ ื‘ืจื™ืื•ืชื• ื•ื›ื•ืฉืจื• ื”ื’ื•ืคื ื™, ืื• ื”ืคื ืชื” ืื•ืชื• ืœืื‘ื—ื•ืŸ ื•ืœืฉื™ืงื•ื ืžืงืฆื•ืขื™. ื”ื•ื ืžืงื‘ืœ ื“ืžื™ ืื‘ื˜ืœื” ื”ื ืžื•ื›ื™ื ืžืกื›ื•ื ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ืฉื™ืจื•ืช ื”ืชืขืกื•ืงื” ื”ืคื ื” ืื•ืชื• ืœื”ืฉืชืœืžื•ืช ืื• ืœื”ืกื‘ื” ืžืงืฆื•ืขื™ืช ื”ื ื™ืชื ื•ืช ื‘ืฉืขื•ืช ื”ื™ื•ื ื•ื‘ืžืฉืš 12 ื—ื•ื“ืฉื™ื ืœื›ืœ ื”ื™ื•ืชืจ, ื•ื”ื•ื ืžืฉืชืชืฃ ื‘ืœื™ืžื•ื“ื™ื ื‘ืื•ืคืŸ ืกื“ื™ืจ. ื”ื•ื ืฉื›ื™ืจ ืฉื”ื›ื ืกืชื• ืžืขื‘ื•ื“ื” ื ืžื•ื›ื” ืžืกื›ื•ื ืžื”ืกื›ื•ื ืฉื ืงื‘ืข ื‘ื˜ื‘ืœื” ืœืคื™ ื ืชื•ื ื™ื• ื”ืื™ืฉื™ื™ื. ื”ื•ื ืขื•ื‘ื“ ื‘ืžืคืขืœ ืžื•ื’ืŸ ื‘ื”ื™ืงืฃ ื”ืขื‘ื•ื“ื” ื”ืžืงื•ื‘ืœ ื‘ืื•ืชื• ืžืคืขืœ. ื”ื•ื ืขืฆืžืื™ ืขื ื”ื›ื ืกื•ืช ื ืžื•ื›ื•ืช. ื›ืžื• ื›ืŸ, ื™ื›ื•ืœื™ื ืœื”ื’ื™ืฉ ืชื‘ื™ืขื” ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืžื‘ืœื™ ืœืขื ื•ืช ืขืœ ื”ืงืจื™ื˜ืจื™ื•ื ื™ื ืฉืฆื•ื™ื ื•: ืœืžื™ื“ืข ื ื•ืกืฃ ืจืื•: ื ืฉื™ื ื”ืฆืคื•ื™ื•ืช ืœืฉื”ื•ืช ื‘ืžืงืœื˜ ืœื ืฉื™ื ื ืคื’ืขื•ืช ืืœื™ืžื•ืช ืžืขืœ 30 ื™ืžื™ื. ืืกื™ืจื™ื ืžืฉื•ื—ืจืจื™ื ืฉืฉื”ื• ื‘ื›ืœื ื™ื•ืชืจ ืžื—ืฆื™ ืฉื ื”. ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœืืกื™ืจื™ื ืžืฉื•ื—ืจืจื™ื.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”',
    [
        'passage: ืžื“ืจื™ืš ืœืงื‘ืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื’ื•ื‘ื” ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ืกื›ื•ืžื™ื ืฉืœื ื ืœืงื—ื™ื ื‘ื—ืฉื‘ื•ืŸ ืœืฆื•ืจืš ื—ื™ืฉื•ื‘ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืขืœ ืžื‘ืงืฉ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœื“ื•ื•ื— ืขืœ ื”ื›ื ืกื•ืชื™ื• ื›ื“ื™ ืœื‘ื“ื•ืง ื–ื›ืื•ืช ืœืงื‘ืœื” ื•ืœื—ืฉื‘ ืืช ืฉื•ื•ื™ื”. ืขื ื–ืืช, ื”ื”ื›ื ืกื•ืช ื”ื‘ืื•ืช ืœื ื ื›ืœืœื•ืช ื‘ื—ื™ืฉื•ื‘ ื–ื”: ืงืฆื‘ืช ื™ืœื“ื™ื ื’ืžืœืช ื™ืœื“ ื ื›ื” ืงืฆื‘ืช ืฉื™ืจื•ืชื™ื ืžื™ื•ื—ื“ื™ื ื’ืžืœืช ื ื™ื™ื“ื•ืช ื’ืžืœืช ืกื™ืขื•ื“ ื“ืžื™ ืžื—ื™ื” ืœืืœืžื ื” ื•ืœื™ืชื•ื ืงืฆื‘ืื•ืช ืžื™ื•ื—ื“ื•ืช ืœื ื›ื™ ืขื‘ื•ื“ื” ืงืฆื‘ื” ืื• ื”ื˜ื‘ื” ื”ืžืฉื•ืœืžืช ืœื ื–ืงืงื™ื ืขืœ ืคื™ ื—ื•ืง ืฉื™ืจื•ืชื™ ื”ืกืขื“ ืชืฉืœื•ืžื™ื ืฉื”ืงื•ื ื’ืจืก ื”ื™ื”ื•ื“ื™ ื”ืขื•ืœืžื™ ืžืฉืœื ืœื—ืกื™ื“ื™ ืื•ืžื•ืช ื”ืขื•ืœื ืชืžื™ื›ื” ื›ืกืคื™ืช ื”ื ื™ืชื ืช ื›ืกื™ื•ืข ื‘ืชืฉืœื•ื ืฉื›ืจ ื“ื™ืจื” ืœืžื™ ืฉืžืฉื›ื™ืจ ืืช ื“ื™ืจืชื• ื•ืฉื•ื›ืจ ื“ื™ืจื” ืื—ืจืช ืœืžื’ื•ืจื™ื•, ืœื ืชื™ืœืงื— ื‘ื—ืฉื‘ื•ืŸ ื”ื”ื›ื ืกื” ืžื”ืฉื›ืจืช ื“ื™ืจืชื• ืฉืื™ื ื” ืขื•ืœื” ืขืœ ืกื›ื•ื ื“ืžื™ ื”ืฉื›ื™ืจื•ืช ืฉื”ื•ื ืžืฉืœื (ื”ื—ืœ ืžื”-01.01.2019) ืชืฉืœื•ืžื™ ืžื–ื•ื ื•ืช ืœืื™ืฉื” ืื• ืœื™ืœื“ื™ื, ื›ืœ ืขื•ื“ ื”ื ืœื ืขื•ืœื™ื ืขืœ ืกื›ื•ื ืงืฆื‘ืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื”ืžื’ื™ืขื” ืœื•. ืื ืื“ื ื ืชืžืš ื›ืกืคื™ืช ื‘ืื•ืคืŸ ืงื‘ื•ืข ื•ืœืœื ืชืžื•ืจื” ืžื‘ื ื™ ืžืฉืคื—ื” ืื• ืžื’ื•ืจื ื‘ืงื”ื™ืœื” ื›ื’ื•ืŸ ืขืžื•ืชื”, ื”ืกื›ื•ื ืœื ื™ื—ืฉื‘ ื›ื”ื›ื ืกื” ืœืฆื•ืจืš ื”ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ืขื ื–ืืช, ืกื›ื•ืžื™ ืชืžื™ื›ื” ื’ื‘ื•ื”ื™ื ื‘ืื•ืคืŸ ื—ืจื™ื’ ืขืœื•ืœื™ื ืœืคื’ื•ืข ื‘ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ืชืฉืœื•ืžื™ื ืฉื”ื—ื•ืง ืœื ืงื•ื‘ืข ืœื’ื‘ื™ื”ื ื‘ืžืคื•ืจืฉ ื›ื™ ื”ื ืื™ื ื ื ื—ืฉื‘ื™ื ืœื”ื›ื ืกื”, ื™ื•ื‘ืื• ื‘ื—ืฉื‘ื•ืŸ ื‘ืžืกื’ืจืช ืžื‘ื—ืŸ ื”ื”ื›ื ืกื•ืช. ื›ืžื• ื›ืŸ, ื™ืฉื ื ืžืขื ืงื™ื ืฉื ืงื‘ืข ื‘ืžืคื•ืจืฉ ื‘ื—ื•ืง ื›ื™ ื”ื ื™ื™ื—ืฉื‘ื• ื›ื”ื›ื ืกื”. ืœืžื™ื“ืข ื ื•ืกืฃ ืจืื•: ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ("ื”ื›ื ืกื•ืช ื•ื ื›ืกื™ื")',
        'passage: ืžื“ืจื™ืš ืœืงื‘ืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื’ื•ื‘ื” ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื’ื•ืจืžื™ื ืฉื ืœืงื—ื™ื ื‘ื—ืฉื‘ื•ืŸ ืœืฆื•ืจืš ื—ื™ืฉื•ื‘ ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื‘ืขืช ื‘ืงืฉืช ื”ื”ื‘ื˜ื—ื” ื™ืฉ ืœื“ื•ื•ื— ืขืœ ื”ื”ื›ื ืกื•ืช ื•ื”ื ื›ืกื™ื ื”ื‘ืื™ื: ื”ื›ื ืกื•ืช ืžืขื‘ื•ื“ื” ืฉื•ื•ื™ ืจื›ื‘ ื ื›ืกื™ื ืคื™ื ื ืกื™ื™ื ื›ื’ื•ืŸ ื—ืกื›ื•ื ื•ืช ื•ืคืง"ืž. ืฉื•ื•ื™ ืขืจืš ื ื“ืœ"ืŸ ื›ืคื™ ืฉื™ื™ืงื‘ืข ืขืœ ื™ื“ื™ ืฉืžืื™ ืžื•ืกืžืš ืžื˜ืขื ื”ืžื•ืกื“ ืœื‘ื™ื˜ื•ื— ืœืื•ืžื™ ื•ื‘ื”ืชืื ืœืžืฆื‘ ื”ืžืฉืคื—ืชื™, ืžืกืคืจ ื”ื™ืœื“ื™ื ื•ื’ื™ืœ ืžื‘ืงืฉ ื”ื’ืžืœื”. ืœืžื™ื“ืข ื ื•ืกืฃ ืจืื•: ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ("ื”ื›ื ืกื•ืช ื•ื ื›ืกื™ื") ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื•ื‘ืขืœื•ืช ืขืœ ืจื›ื‘',
        'passage: ื”ื’ื‘ืœืช ืฉื›ืจ ื˜ืจื—ื” ืขื‘ื•ืจ ืกื™ื•ืข ืื• ื™ื™ืฆื•ื’ ื‘ืชื‘ื™ืขื” ืœืงืฆื‘ืช ื ื›ื•ืช ื•ืžืขื ืง ื ื›ื•ืช ืœื ืคื’ืขื™ ืขื‘ื•ื“ื” ื—ื™ืฉื•ื‘ ืฉื›ืจ ื”ื˜ืจื—ื” ื‘ืžืงืจื™ื ื‘ื”ื ื”ืชื•ื‘ืข ืงื™ื‘ืœ ื’ืžืœื” ืœืคื ื™ ืฉื”ื’ื™ืฉ ืืช ื”ืชื‘ื™ืขื” ื›ืืฉืจ ื”ืชื•ื‘ืข ืงื™ื‘ืœ ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื•ื›ืชื•ืฆืื” ืžื”ืชื‘ื™ืขื” ื”ื•ื ืžืงื‘ืœ ืงืฆื‘ืช ื ื›ื•ืช ืœื ืคื’ืขื™ ืขื‘ื•ื“ื” ื‘ื ื•ืกืฃ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ืœืฉื›ืจ ื”ื˜ืจื—ื” ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,800 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืขื‘ื•ื“ื”, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ื” ื‘ืกืš 2,400 โ‚ช. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” 907 โ‚ช ื•-17% ืžื”ืงืฆื‘ื” ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื (ืจืื• ื˜ื‘ืœื” ืœืขื™ืœ). ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ื•ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื”ื•ืคืกืงื” ื‘ืขืงื‘ื•ืช ืงื‘ื™ืขืช ื”ื–ื›ืื•ืช ืœืงืฆื‘ืช ื”ื ื›ื•ืช, ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื—ื•ืฉื‘ ืขืœ ืคื™ ื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช, ื•ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,400 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืขื‘ื•ื“ื”, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ืช ื ื›ื•ืช ื‘ืกืš 3,800 โ‚ช. ื‘ืขืงื‘ื•ืช ืงื‘ืœืช ืงืฆื‘ืช ื”ื ื›ื•ืช, ื ืžืฆื ืฉื”ืชื•ื‘ืข ื›ื‘ืจ ืื™ื ื• ื–ื›ืื™ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ืฉืงื™ื‘ืœ, ื•ื–ื• ื”ื•ืคืกืงื”. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” ืกื›ื•ื ื”ื™ืกื•ื“ ื‘ืกืš 907 โ‚ช ื•-17% ืžื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช (17% ืž-2,400 โ‚ช, ืฉื”ื 408 โ‚ช) ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื.',
        'passage: ื”ื’ื‘ืœืช ืฉื›ืจ ื˜ืจื—ื” ืขื‘ื•ืจ ืกื™ื•ืข ืื• ื™ื™ืฆื•ื’ ื‘ืชื‘ื™ืขื” ืœื’ืžืœืช ื ื›ื•ืช ืžืชื ื“ื‘ื™ื ื—ื™ืฉื•ื‘ ืฉื›ืจ ื”ื˜ืจื—ื” ื‘ืžืงืจื™ื ื‘ื”ื ื”ืชื•ื‘ืข ืงื™ื‘ืœ ื’ืžืœื” ืœืคื ื™ ืฉื”ื’ื™ืฉ ืืช ื”ืชื‘ื™ืขื” ืชื•ื‘ืข ืฉืงื™ื‘ืœ ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื•ื›ืชื•ืฆืื” ืžื”ืชื‘ื™ืขื” ื”ื•ื ืžืงื‘ืœ ืงืฆื‘ืช ื ื›ื•ืช ื‘ื ื•ืกืฃ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ืœืฉื›ืจ ื”ื˜ืจื—ื” ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,800 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืชื ื“ื‘ื™ื, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ื” ื‘ืกืš 2,400 โ‚ช. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” 907 โ‚ช ื•-17% ืžื”ืงืฆื‘ื” ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื (ืจืื• ื˜ื‘ืœื” ืœืขื™ืœ). ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ื•ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื”ื•ืคืกืงื” ื‘ืขืงื‘ื•ืช ืงื‘ื™ืขืช ื”ื–ื›ืื•ืช ืœืงืฆื‘ืช ื”ื ื›ื•ืช, ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื—ื•ืฉื‘ ืขืœ-ืคื™ ื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช, ื•ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,400 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืชื ื“ื‘ื™ื, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ืช ื ื›ื•ืช ื‘ืกืš 3,800 โ‚ช. ื‘ืขืงื‘ื•ืช ืงื‘ืœืช ืงืฆื‘ืช ื”ื ื›ื•ืช, ื ืžืฆื ืฉื”ืชื•ื‘ืข ื›ื‘ืจ ืื™ื ื• ื–ื›ืื™ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ืฉืงื™ื‘ืœ, ื•ื–ื• ื”ื•ืคืกืงื”. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” 907 โ‚ช ื•-17% ืžื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช (17% ืž-2,400 โ‚ช, ืฉื”ื 408 โ‚ช) ื‘ื›ืœ ื—ื•ื“ืฉ, ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื.',
        'passage: ืžื“ืจื™ืš ืœืงื‘ืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืื• ื”ืฉืœืžืช ื”ื›ื ืกื” ืžื™ ืฉืขื•ืžื“ ื‘ืชื ืื™ ื”ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ื™ื›ื•ืœ ืœื”ื™ื•ืช ื–ื›ืื™ ืœื’ืžืœื” ืžืœืื”, ืื• ืœื’ืžืœื” ื—ืœืงื™ืช ื”ื™ื“ื•ืขื” ื’ื ื‘ืฉื "ื”ืฉืœืžืช ื”ื›ื ืกื”". ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืžืชืงื™ื™ืžืช ืื ืžืชืงื™ื™ืžื™ื 3 ืชื ืื™ื ืžืฆื˜ื‘ืจื™ื: ืชื•ืฉื‘ื•ืช ื‘ื™ืฉืจืืœ ืœืžืฉืš 24 ื—ื•ื“ืฉื™ื ืจืฆื•ืคื™ื, ืœืžืขื˜ ื‘ืžืงืจื™ื ืžื™ื•ื—ื“ื™ื. ื’ื™ืœ ื”ืžื‘ืงืฉ ืžืขืœ 20, ืœืžืขื˜ ื‘ืžืงืจื™ื ืžื™ื•ื—ื“ื™ื. ื”ืžื‘ืงืฉ ืจืฉื•ื ื‘ืœืฉื›ืช ื”ืชืขืกื•ืงื” ืื• ืžืชื™ื™ืฆื‘ ื‘ื” ื‘ื”ืชืื ืœื”ื ื—ื™ื•ืชื™ื”, ื‘ืฉืœ ืื—ืช ืžื”ืกื™ื‘ื•ืช ื”ื‘ืื•ืช: ื”ื•ื ืžื—ื•ืกืจ ืขื‘ื•ื“ื” ื•ืœืฉื›ืช ื”ืชืขืกื•ืงื” ื˜ืจื ื”ืฆื™ืขื” ืœื• ืขื‘ื•ื“ื” ื”ืชื•ืืžืช ืืช ืžืฆื‘ ื‘ืจื™ืื•ืชื• ื•ื›ื•ืฉืจื• ื”ื’ื•ืคื ื™, ืื• ื”ืคื ืชื” ืื•ืชื• ืœืื‘ื—ื•ืŸ ื•ืœืฉื™ืงื•ื ืžืงืฆื•ืขื™. ื”ื•ื ืžืงื‘ืœ ื“ืžื™ ืื‘ื˜ืœื” ื”ื ืžื•ื›ื™ื ืžืกื›ื•ื ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ืฉื™ืจื•ืช ื”ืชืขืกื•ืงื” ื”ืคื ื” ืื•ืชื• ืœื”ืฉืชืœืžื•ืช ืื• ืœื”ืกื‘ื” ืžืงืฆื•ืขื™ืช ื”ื ื™ืชื ื•ืช ื‘ืฉืขื•ืช ื”ื™ื•ื ื•ื‘ืžืฉืš 12 ื—ื•ื“ืฉื™ื ืœื›ืœ ื”ื™ื•ืชืจ, ื•ื”ื•ื ืžืฉืชืชืฃ ื‘ืœื™ืžื•ื“ื™ื ื‘ืื•ืคืŸ ืกื“ื™ืจ. ื”ื•ื ืฉื›ื™ืจ ืฉื”ื›ื ืกืชื• ืžืขื‘ื•ื“ื” ื ืžื•ื›ื” ืžืกื›ื•ื ืžื”ืกื›ื•ื ืฉื ืงื‘ืข ื‘ื˜ื‘ืœื” ืœืคื™ ื ืชื•ื ื™ื• ื”ืื™ืฉื™ื™ื. ื”ื•ื ืขื•ื‘ื“ ื‘ืžืคืขืœ ืžื•ื’ืŸ ื‘ื”ื™ืงืฃ ื”ืขื‘ื•ื“ื” ื”ืžืงื•ื‘ืœ ื‘ืื•ืชื• ืžืคืขืœ. ื”ื•ื ืขืฆืžืื™ ืขื ื”ื›ื ืกื•ืช ื ืžื•ื›ื•ืช. ื›ืžื• ื›ืŸ, ื™ื›ื•ืœื™ื ืœื”ื’ื™ืฉ ืชื‘ื™ืขื” ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืžื‘ืœื™ ืœืขื ื•ืช ืขืœ ื”ืงืจื™ื˜ืจื™ื•ื ื™ื ืฉืฆื•ื™ื ื•: ืœืžื™ื“ืข ื ื•ืกืฃ ืจืื•: ื ืฉื™ื ื”ืฆืคื•ื™ื•ืช ืœืฉื”ื•ืช ื‘ืžืงืœื˜ ืœื ืฉื™ื ื ืคื’ืขื•ืช ืืœื™ืžื•ืช ืžืขืœ 30 ื™ืžื™ื. ืืกื™ืจื™ื ืžืฉื•ื—ืจืจื™ื ืฉืฉื”ื• ื‘ื›ืœื ื™ื•ืชืจ ืžื—ืฆื™ ืฉื ื”. ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœืืกื™ืจื™ื ืžืฉื•ื—ืจืจื™ื.',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Correlation

Metric Value
pearson 0.5301
spearman 0.4791

Training Details

Training Dataset

Unnamed Dataset

  • Size: 32,540 training samples
  • Columns: query, paragraph, and labels
  • Approximate statistics based on the first 1000 samples:
    query paragraph labels
    type string string float
    details
    • min: 21 characters
    • mean: 50.28 characters
    • max: 100 characters
    • min: 94 characters
    • mean: 982.24 characters
    • max: 1817 characters
    • min: 0.0
    • mean: 0.19
    • max: 1.0
  • Samples:
    query paragraph labels
    query: ืžื” ื”ืชืฉืœื•ื ืขื‘ื•ืจ ื“ืจื’ื” X ื‘ืžืขื•ืŸ ืื• ืžืฉืคื—ืชื•ืŸ? ืžื” ื”ื–ื›ืื•ืช ืขื‘ื•ืจ ื™ืœื“ ื ื•ืกืฃ ื‘ืžืกื’ืจืช ืžืขื•ืŸ passage: ื“ืจื’ื•ืช ื”ืฉืชืชืคื•ืช ื‘ืžื™ืžื•ืŸ ืžืขื•ื ื•ืช ื™ื•ื ื•ืžืฉืคื—ืชื•ื ื™ื ื’ื•ื‘ื” ืฉื›ืจ ื”ืœื™ืžื•ื“ ืกื›ื•ืžื™ ื”ืฉืชืชืคื•ืช ื”ืžื“ื™ื ื” ื•ื”ืกื›ื•ืžื™ื ืื•ืชื ืžืฉืœื™ืžื™ื ื”ื”ื•ืจื™ื ืขื‘ื•ืจ ื›ืœ ืื—ืช ืžื”ื“ืจื’ื•ืช, ืžืคื•ืจื˜ื™ื ื‘ื˜ื‘ืœืื•ืช ืฉื›ืจ ืœื™ืžื•ื“. ื”ื˜ื‘ืœืื•ืช ืžื—ื•ืœืงื•ืช ืœืคื™ ืชืขืจื™ืคื™ื ืœื™ืœื“ื™ื ื•ืชืขืจื™ืคื™ื ืœืชื™ื ื•ืงื•ืช: ื’ื•ื‘ื” ืฉื›ืจ ื”ืœื™ืžื•ื“ ื‘ื”ืชืื ืœื“ืจื’ื•ืช ื”ืฉื•ื ื•ืช ืžืคื•ืจื˜ืช ื‘ื˜ื‘ืœืื•ืช ืฉื›ืจ ืœื™ืžื•ื“ ื‘ืžืกื’ืจื•ืช ื™ืœื“ื™ื ื‘ืืชืจ ืžืฉืจื“ ื”ืขื‘ื•ื“ื”. ื”ื“ืจื’ื•ืช ื”ืžื•ืคื™ืขื•ืช ื‘ื˜ื‘ืœืื•ืช ืžื•ืชืืžื•ืช ืœื’ื•ื‘ื” ื”ื”ื›ื ืกื” ืœื ืคืฉ ื‘ืžืฉืคื—ื”. ื›ื›ืœ ืฉื“ืจื’ืช ื”ื–ื›ืื•ืช (ื‘ื˜ื•ื•ื— 12-3) ื ืžื•ื›ื” ื™ื•ืชืจ, ื›ืš ื’ื“ืœื” ื”ืฉืชืชืคื•ืช ื”ืžื“ื™ื ื” ื‘ืชืฉืœื•ื. ืขื‘ื•ืจ ืจืžื•ืช ื”ื”ืฉืชืชืคื•ืช ื”ืžื•ืชืืžื•ืช ืœื’ื•ื‘ื” ื”ื”ื›ื ืกื•ืช, ื™ืฉ ืœื”ื•ืกื™ืฃ ืื• ืœื”ืคื—ื™ืช ื“ืจื’ื•ืช, ืขืœ-ืคื™ ืžืกืคืจ ืžืกืคืจ ื”ื™ืœื“ื™ื ื”ืฉื•ื”ื™ื ื‘ืžืขื•ืŸ ืื• ื‘ืžืฉืคื—ืชื•ืŸ - ืœืžืฉืคื—ื” ืขื ื›ืžื” ื™ืœื“ื™ื ื”ืฉื•ื”ื™ื ื‘ืžืขื•ืŸ ืื• ื‘ืžืฉืคื—ืชื•ืŸ, ืชื•ื’ื“ืœ ืจืžืช ื”ืฉืชืชืคื•ืช ื”ืžื“ื™ื ื” ืขื‘ื•ืจ ื›ืœ ืื—ื“ ืžื”ื™ืœื“ื™ื (ืชื™ืงื‘ืข ื“ืจื’ื” ื ืžื•ื›ื” ื™ื•ืชืจ ื‘ื™ืŸ ื”ื“ืจื’ื•ืช 12-3). ืชื™ื ื•ืงื•ืช ื”ื ืžื™ ืฉื’ื™ืœื ื”ื™ื” ืขื“ 15 ื—ื•ื“ืฉื™ื ื‘-1 ื‘ืกืคื˜ืžื‘ืจ ืฉืœ ืฉื ืช ื”ืœื™ืžื•ื“ื™ื ืืœื™ื” ื ืจืฉืžื•. ื™ืœื“ื™ื ื”ื ืžื™ ืฉื‘-1 ื‘ืกืคื˜ืžื‘ืจ ืฉืœ ืฉื ืช ื”ืœื™ืžื•ื“ื™ื ืืœื™ื” ื ืจืฉืžื•, ื’ื™ืœื ื”ื™ื” ื‘ื™ืŸ 15 ื—ื•ื“ืฉื™ื ื•ื™ื•ื ืœ-33 ื—ื•ื“ืฉื™ื (ืื• ืขื“ ืœื’ื™ืœ 46 ื—ื•ื“ืฉื™ื, ืœืžื™ ืฉื™ืฉ ืœื”ื ืื™ืฉื•ืจ ืžื”ื™ื—ื™ื“ื” ืœื”ืชืคืชื—ื•ืช ื”ื™ืœื“ ื›ื™ ื”ื ืžืขื•ื›ื‘ื™ ื”ืชืคืชื—ื•ืช). ื”ืฉืคืขืช ืžืกืคืจ ื”ื™ืœื“ื™ื ื”ืฉื•ื”ื™ื ื‘ืžืขื•ืŸ/ืžืฉืคื—ืชื•ืŸ ืขืœ ื“ืจื’ืช ื”... 0.5
    query: ืžื” ื”ืชืฉืœื•ื ืขื‘ื•ืจ ื“ืจื’ื” X ื‘ืžืขื•ืŸ ืื• ืžืฉืคื—ืชื•ืŸ? ืžื” ื”ื–ื›ืื•ืช ืขื‘ื•ืจ ื™ืœื“ ื ื•ืกืฃ ื‘ืžืกื’ืจืช ืžืขื•ืŸ passage: ืกื™ื•ืข ืœื”ื•ืจื™ื ืขืฆืžืื™ื™ื (ื”ื•ืจื™ื ื™ื—ื™ื“ื™ื) ื‘ืžื™ืžื•ืŸ ืžืขื•ื ื•ืช ื™ื•ื ื•ืžืฉืคื—ืชื•ื ื™ื ื”ื•ืจื™ื ืขืฆืžืื™ื™ื (ื”ื•ืจื™ื ื™ื—ื™ื“ื™ื) (/he/ื”ื•ืจื”_ืขืฆืžืื™_(ื”ื•ืจื”_ื™ื—ื™ื“)) ืขืฉื•ื™ื™ื ืœื”ื™ื•ืช ื–ื›ืื™ื ืœืกื™ื•ืข ื‘ืžื™ืžื•ืŸ ืžืขื•ื ื•ืช ื™ื•ื ื•ืžืฉืคื—ืชื•ื ื™ื ืœืคื™ ื“ืจื’ื•ืช ื”ืฉืชืชืคื•ืช (/he/ื“ืจื’ื•ืช_ื”ืฉืชืชืคื•ืช_ื‘ืžื™ืžื•ืŸ_ืžืขื•ื ื•ืช_ื™ื•ื_ื•ืžืฉืคื—ืชื•ื ื™ื) ืฉื ืงื‘ืขื•ืช ื‘ื”ืชืื ืœืจืžืช ื”ื”ื›ื ืกื” ืฉืœื”ื (/he/ืจืžืช_ื”ื”ื›ื ืกื”_ืœื ืคืฉ_ืœืฆื•ืจืš_ืกื™ื•ืข_ื‘ืžื™ืžื•ืŸ_ืžืขื•ื ื•ืช_ื™ื•ื) ื”ื•ืจื™ื ืขืฆืžืื™ื™ื ืฉืขื•ื ื™ื ืขืœ ื”ื’ื“ืจืช ืžื’ื‘ื™ืจื™ ืขื‘ื•ื“ื” (.D7.96.D7.9B.D7.90.D7.95.D7.AA_.D7.A9.D7.9C_.D7.94.D7.95.D7.A8.D7.99.D7.9D_.D7.9E.D7.92.D7.91.D7.99.D7.A8.D7.99_.D7.A2.D7.91.D7.95.D7.93.D7.94) ื–ื›ืื™ื ืœืกื™ื•ืข ืžื•ื’ื“ืœ ื•ื™ืฉืœืžื• 250 ื‘ื—ื•ื“ืฉ ืœื™ืœื“ ืื—ื“ ื•-375 ื‘ื—ื•ื“ืฉ ืœืฉื ื™ ื™ืœื“ื™ื ื›ื“ื™ ืœื”ืงืœ ืขืœ ืฉื™ืœื•ื‘ื ืฉืœ ื”ื•ืจื™ื ื‘ืฉื•ืง ื”ืขื‘ื•ื“ื”, ื”ืžื“ื™ื ื” ืžืกื™ื™ืขืช ืœื”ื ื‘ืžื™ืžื•ืŸ ืžืขื•ื ื•ืช ื™ื•ื ื•ืžืฉืคื—ืชื•ื ื™ื ืžื•ื›ืจื™ื. ื’ื•ื‘ื” ื”ืชืžื™ื›ื” ื‘ื–ื›ืื•ืช ื”ื›ืœืœื™ืช ืฉืœ ื”ื”ื•ืจื™ื (ื–ื•ื’ื•ืช ื”ื•ืจื™ื ืื• ื”ื•ืจื™ื ืขืฆืžืื™ื™ื) ื ืงื‘ืข ืขืœ-ืคื™ ืžืกืคืจ ื“ืจื’ื•ืช ื”ืฉืชืชืคื•ืช ื”ืžืชื‘ืกืกื•ืช ืขืœ ืจืžืช ื”ื”ื›ื ืกื” ืœื ืคืฉ ื‘ืžืฉืคื—ื”. ื”ื•ืจื™ื ืขืฆืžืื™ื™ื (ื”ื•ืจื™ื ื™ื—ื™ื“ื™ื) ืฉืขื•ื ื™ื ืขืœ ื”ื’ื“ืจืช "ืžื’ื‘ื™ืจื™ ืขื‘ื•ื“ื”" (ื‘ื”ืชืื ืœืžืคื•ืจื˜ ื‘ื”ืžืฉืš), ื–ื›ืื™ื ืœืกื™ื•ืข ืžื•ื’ื“ืœ ื•ื™ืฉืœืžื• ืจืง 250 โ‚ช ื‘ื—ื•ื“ืฉ ืขื‘ื•ืจ ื™ืœื“ ืื—ื“ ื•-375 โ‚ช ื‘ื—ื•ื“ืฉ ืขื‘ื•ืจ ืฉื ื™ ื™ืœื“ื™ื. ืœืคืจื˜ื™ื ื•ืžื™ื“ืข ื›ืœืœื™... 0.25
    query: ืžื” ื”ืชืฉืœื•ื ืขื‘ื•ืจ ื“ืจื’ื” X ื‘ืžืขื•ืŸ ืื• ืžืฉืคื—ืชื•ืŸ? ืžื” ื”ื–ื›ืื•ืช ืขื‘ื•ืจ ื™ืœื“ ื ื•ืกืฃ ื‘ืžืกื’ืจืช ืžืขื•ืŸ passage: ื”ืฉืชืชืคื•ืช ื‘ืžื™ืžื•ืŸ ืžืขื•ื ื•ืช ื™ื•ื ื•ืžืฉืคื—ืชื•ื ื™ื ืชื”ืœื™ืš ืžื™ืžื•ืฉ ื”ื–ื›ื•ืช ืื™ืชื•ืจ ืžืกื’ืจืช ืžื•ื›ืจืช ืžืขืจื›ืช ืื™ื ื˜ืจื ื˜ื™ืช (ืžืงื•ื•ื ืช) ืžืืคืฉืจืช ืœืืชืจ ืžืฉืคื—ืชื•ื ื™ื, ืžืขื•ื ื•ืช ื•ืฆื”ืจื•ื ื™ื ื”ื ืžืฆืื™ื ื‘ืคื™ืงื•ื— ืžืžืฉืœืชื™. ื ื™ืชืŸ ืœื‘ืฆืข ื—ื™ืคื•ืฉ ืœืคื™ ื™ืฉื•ื‘, ืกื•ื’ ื”ืžืกื’ืจืช ืื• ืฉื ื”ืžืกื’ืจืช. ืœื›ื ื™ืกื” ืœืžืขืจื›ืช ืœื—ืฆื• ื›ืืŸ. ื”ืชืฉืœื•ื ืœืžืขื•ืŸ/ืžืฉืคื—ืชื•ืŸ ืขื‘ื•ืจ ื—ื•ื“ืฉ ืื•ื’ื•ืกื˜ ื™ื—ื•ืฉื‘ ืชืฉืœื•ื ื‘ืื•ืคืŸ ื™ื—ืกื™ ื‘ื”ืชืื ืœืชืงื•ืคืช ืฉื”ื•ืช ื”ื™ืœื“ ื‘ืžืขื•ืŸ (ื”ืขืœื•ืช ื”ืžืœืื” ืœื—ื•ื“ืฉ ื›ืคื•ืœ ืžืกืคืจ ื”ื—ื•ื“ืฉื™ื ืฉื”ื™ืœื“ ืฉื”ื” ื‘ืžืขื•ืŸ ื—ืœืงื™ 12 ื—ื•ื“ืฉื™ื). ื”ื—ื–ืจ ื›ืกืคื™ ื‘ื”ืชืื ืœื“ืจื’ืช ื”ื”ืฉืชืชืคื•ืช, ื™ื™ื ืชืŸ ืœื”ื•ืจื™ื ืขื‘ื•ืจ ื”ื—ื•ื“ืฉ ืฉื‘ื• ื”ืชืงื‘ืœ ืฉืืœื•ืŸ ื”ื”ืจืฉืžื” ื‘ืžื•ืงื“, ื•ืขื‘ื•ืจ ื”ื—ื•ื“ืฉ ืฉืงื“ื ืœื•. ื”ืฉืชืชืคื•ืช ื‘ื—ื•ื“ืฉ ื”ืจืืฉื•ืŸ ืœื›ื ื™ืกืช ื”ื™ืœื“ ืœืžืกื’ืจืช (ืžืขื•ืŸ ืื• ืžืฉืคื—ืชื•ืŸ): ื”ื•ืจื™ื• ืฉืœ ื™ืœื“ ืฉื ื›ื ืก ืœืžืกื’ืจืช ืขื“ ืœ-15 ื‘ื—ื•ื“ืฉ (ื›ื•ืœืœ ื”-15 ืœื—ื•ื“ืฉ), ื™ื”ื™ื• ื–ื›ืื™ื ืœื”ืฉืชืชืคื•ืช ื”ืžื“ื™ื ื” ืขื‘ื•ืจ ืื•ืชื• ื—ื•ื“ืฉ (ืขืœ-ืคื™ ื”ื“ืจื’ื” ืฉื ืงื‘ืขื” ืœื”ื). ื”ื•ืจื™ื• ืฉืœ ื™ืœื“ ืฉื ื›ื ืก ืœืžืกื’ืจืช ืœืื—ืจ ื”-15 ืœื—ื•ื“ืฉ, ืœื ื™ื”ื™ื• ื–ื›ืื™ื ืœื”ืฉืชืชืคื•ืช ื‘ื—ื•ื“ืฉ ื–ื”. ื‘ืžืงืจื” ื–ื” ื™ื—ื•ื™ื‘ื• ื”ื”ื•ืจื™ื ืœืฉืœื ื“ืžื™ ื”ื—ื–ืงื” ื‘ืื•ืคืŸ ื™ื—ืกื™ ืœื™ืžื™ื ื‘ื”ื ืฉื”ื” ื”ื™ืœื“ ื‘ืžืกื’ืจืช. ื”ื™ืขื“ืจื•ืช ืฉืœ ื”ื™ืœื“ ื”ื™ืขื“ืจื•ืช ืžื”ืžืขื•ืŸ ืœืชืงื•ืคื” ืฉืœ ื™ื•ืชืจ ืž-21 ื™ืžื™ื ืชื™ื—ืฉื‘ ื›ืขื–ื™ื‘ื”, ืืœื ืื ื›ืŸ ื”ื•ืฆื’ื• ื‘ืžื”ืœืš ืชืงื•ืคื” ื–ื• ืื™ืฉื•ืจื™ื ืจืคื•ืื™ื™ื ืขืœ ืžื—ืœื” ืื• ืืฉืคื•ื– ืฉืœ ื”ื™ืœื“. ื”ื™ืขื“ืจื•ืช ... 0.5
  • Loss: BinaryCrossEntropyLoss with these parameters:
    {
        "activation_fn": "torch.nn.modules.linear.Identity",
        "pos_weight": null
    }
    

Evaluation Dataset

Unnamed Dataset

  • Size: 8,140 evaluation samples
  • Columns: query, paragraph, and labels
  • Approximate statistics based on the first 1000 samples:
    query paragraph labels
    type string string float
    details
    • min: 26 characters
    • mean: 51.8 characters
    • max: 101 characters
    • min: 33 characters
    • mean: 1021.83 characters
    • max: 1738 characters
    • min: 0.0
    • mean: 0.2
    • max: 1.0
  • Samples:
    query paragraph labels
    query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” passage: ืžื“ืจื™ืš ืœืงื‘ืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื’ื•ื‘ื” ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ืกื›ื•ืžื™ื ืฉืœื ื ืœืงื—ื™ื ื‘ื—ืฉื‘ื•ืŸ ืœืฆื•ืจืš ื—ื™ืฉื•ื‘ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืขืœ ืžื‘ืงืฉ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœื“ื•ื•ื— ืขืœ ื”ื›ื ืกื•ืชื™ื• ื›ื“ื™ ืœื‘ื“ื•ืง ื–ื›ืื•ืช ืœืงื‘ืœื” ื•ืœื—ืฉื‘ ืืช ืฉื•ื•ื™ื”. ืขื ื–ืืช, ื”ื”ื›ื ืกื•ืช ื”ื‘ืื•ืช ืœื ื ื›ืœืœื•ืช ื‘ื—ื™ืฉื•ื‘ ื–ื”: ืงืฆื‘ืช ื™ืœื“ื™ื ื’ืžืœืช ื™ืœื“ ื ื›ื” ืงืฆื‘ืช ืฉื™ืจื•ืชื™ื ืžื™ื•ื—ื“ื™ื ื’ืžืœืช ื ื™ื™ื“ื•ืช ื’ืžืœืช ืกื™ืขื•ื“ ื“ืžื™ ืžื—ื™ื” ืœืืœืžื ื” ื•ืœื™ืชื•ื ืงืฆื‘ืื•ืช ืžื™ื•ื—ื“ื•ืช ืœื ื›ื™ ืขื‘ื•ื“ื” ืงืฆื‘ื” ืื• ื”ื˜ื‘ื” ื”ืžืฉื•ืœืžืช ืœื ื–ืงืงื™ื ืขืœ ืคื™ ื—ื•ืง ืฉื™ืจื•ืชื™ ื”ืกืขื“ ืชืฉืœื•ืžื™ื ืฉื”ืงื•ื ื’ืจืก ื”ื™ื”ื•ื“ื™ ื”ืขื•ืœืžื™ ืžืฉืœื ืœื—ืกื™ื“ื™ ืื•ืžื•ืช ื”ืขื•ืœื ืชืžื™ื›ื” ื›ืกืคื™ืช ื”ื ื™ืชื ืช ื›ืกื™ื•ืข ื‘ืชืฉืœื•ื ืฉื›ืจ ื“ื™ืจื” ืœืžื™ ืฉืžืฉื›ื™ืจ ืืช ื“ื™ืจืชื• ื•ืฉื•ื›ืจ ื“ื™ืจื” ืื—ืจืช ืœืžื’ื•ืจื™ื•, ืœื ืชื™ืœืงื— ื‘ื—ืฉื‘ื•ืŸ ื”ื”ื›ื ืกื” ืžื”ืฉื›ืจืช ื“ื™ืจืชื• ืฉืื™ื ื” ืขื•ืœื” ืขืœ ืกื›ื•ื ื“ืžื™ ื”ืฉื›ื™ืจื•ืช ืฉื”ื•ื ืžืฉืœื (ื”ื—ืœ ืžื”-01.01.2019) ืชืฉืœื•ืžื™ ืžื–ื•ื ื•ืช ืœืื™ืฉื” ืื• ืœื™ืœื“ื™ื, ื›ืœ ืขื•ื“ ื”ื ืœื ืขื•ืœื™ื ืขืœ ืกื›ื•ื ืงืฆื‘ืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื”ืžื’ื™ืขื” ืœื•. ืื ืื“ื ื ืชืžืš ื›ืกืคื™ืช ื‘ืื•ืคืŸ ืงื‘ื•ืข ื•ืœืœื ืชืžื•ืจื” ืžื‘ื ื™ ืžืฉืคื—ื” ืื• ืžื’ื•ืจื ื‘ืงื”ื™ืœื” ื›ื’ื•ืŸ ืขืžื•ืชื”, ื”ืกื›ื•ื ืœื ื™ื—ืฉื‘ ื›ื”ื›ื ืกื” ืœืฆื•ืจืš ื”ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ืขื ื–ืืช, ืกื›ื•ืžื™ ืชืžื™ื›ื” ื’ื‘ื•ื”ื™ื ื‘ืื•ืคืŸ ื—ืจื™ื’ ืขืœื•ืœื™ื ืœืคื’ื•ืข ื‘ื–ื›ืื•ืช ืœื”ื‘ื˜ื—ืช ื”ื›ื ืกื”. ืชืฉืœื•ืžื™ื ืฉื”ื—ื•ืง ืœื ืงื•ื‘ืข ืœื’ื‘ื™ื”ื ื‘ืžืคื•ืจืฉ ื›ื™ ื”ื ืื™ื ื ื ื—ืฉื‘ื™ื ืœื”ื›ื ืกื”, ื™ื•ื‘ืื• ื‘ื—ืฉื‘ื•ืŸ ื‘ืžืกื’ืจืช ืžื‘ื—ืŸ ื”ื”... 0.0
    query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” passage: ืžื“ืจื™ืš ืœืงื‘ืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื’ื•ื‘ื” ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื’ื•ืจืžื™ื ืฉื ืœืงื—ื™ื ื‘ื—ืฉื‘ื•ืŸ ืœืฆื•ืจืš ื—ื™ืฉื•ื‘ ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื‘ืขืช ื‘ืงืฉืช ื”ื”ื‘ื˜ื—ื” ื™ืฉ ืœื“ื•ื•ื— ืขืœ ื”ื”ื›ื ืกื•ืช ื•ื”ื ื›ืกื™ื ื”ื‘ืื™ื: ื”ื›ื ืกื•ืช ืžืขื‘ื•ื“ื” ืฉื•ื•ื™ ืจื›ื‘ ื ื›ืกื™ื ืคื™ื ื ืกื™ื™ื ื›ื’ื•ืŸ ื—ืกื›ื•ื ื•ืช ื•ืคืง"ืž. ืฉื•ื•ื™ ืขืจืš ื ื“ืœ"ืŸ ื›ืคื™ ืฉื™ื™ืงื‘ืข ืขืœ ื™ื“ื™ ืฉืžืื™ ืžื•ืกืžืš ืžื˜ืขื ื”ืžื•ืกื“ ืœื‘ื™ื˜ื•ื— ืœืื•ืžื™ ื•ื‘ื”ืชืื ืœืžืฆื‘ ื”ืžืฉืคื—ืชื™, ืžืกืคืจ ื”ื™ืœื“ื™ื ื•ื’ื™ืœ ืžื‘ืงืฉ ื”ื’ืžืœื”. ืœืžื™ื“ืข ื ื•ืกืฃ ืจืื•: ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ("ื”ื›ื ืกื•ืช ื•ื ื›ืกื™ื") ื–ื›ืื•ืช ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื•ื‘ืขืœื•ืช ืขืœ ืจื›ื‘ 0.0
    query: ืžื” ืกื›ื•ื ื”ื”ื›ื ืกื” ื”ื ืžื•ืš ืฉื‘ื’ื™ื ื• ืืคืฉืจ ืœืงื‘ืœ ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” passage: ื”ื’ื‘ืœืช ืฉื›ืจ ื˜ืจื—ื” ืขื‘ื•ืจ ืกื™ื•ืข ืื• ื™ื™ืฆื•ื’ ื‘ืชื‘ื™ืขื” ืœืงืฆื‘ืช ื ื›ื•ืช ื•ืžืขื ืง ื ื›ื•ืช ืœื ืคื’ืขื™ ืขื‘ื•ื“ื” ื—ื™ืฉื•ื‘ ืฉื›ืจ ื”ื˜ืจื—ื” ื‘ืžืงืจื™ื ื‘ื”ื ื”ืชื•ื‘ืข ืงื™ื‘ืœ ื’ืžืœื” ืœืคื ื™ ืฉื”ื’ื™ืฉ ืืช ื”ืชื‘ื™ืขื” ื›ืืฉืจ ื”ืชื•ื‘ืข ืงื™ื‘ืœ ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื•ื›ืชื•ืฆืื” ืžื”ืชื‘ื™ืขื” ื”ื•ื ืžืงื‘ืœ ืงืฆื‘ืช ื ื›ื•ืช ืœื ืคื’ืขื™ ืขื‘ื•ื“ื” ื‘ื ื•ืกืฃ ืœื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ืœืฉื›ืจ ื”ื˜ืจื—ื” ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,800 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืขื‘ื•ื“ื”, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื” ื”ืชืงื‘ืœื” ื•ื ืงื‘ืขื” ืงืฆื‘ื” ื‘ืกืš 2,400 โ‚ช. ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื”ื™ื” 907 โ‚ช ื•-17% ืžื”ืงืฆื‘ื” ืœืžืฉืš 60 ื—ื•ื“ืฉื™ื (ืจืื• ื˜ื‘ืœื” ืœืขื™ืœ). ืื ืœืคื ื™ ื”ื’ืฉืช ื”ืชื‘ื™ืขื” ืฉื•ืœืžื” ืœืžื‘ื•ื˜ื— ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื”, ื•ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื”ื›ื ืกื” ื”ื•ืคืกืงื” ื‘ืขืงื‘ื•ืช ืงื‘ื™ืขืช ื”ื–ื›ืื•ืช ืœืงืฆื‘ืช ื”ื ื›ื•ืช, ืฉื›ืจ ื”ื˜ืจื—ื” ื™ื—ื•ืฉื‘ ืขืœ ืคื™ ื”ื”ืคืจืฉ ื‘ื™ืŸ ื”ืงืฆื‘ืื•ืช, ื•ื™ืชื•ื•ืกืฃ ืชืฉืœื•ื ืกื›ื•ื ื™ืกื•ื“ (907 โ‚ช ื ื›ื•ืŸ ืœ-2024). ืœืžื‘ื•ื˜ื— ืฉื•ืœืžื” ื’ืžืœืช ื”ื‘ื˜ื—ืช ื”ื›ื ืกื” ื‘ืกืš 1,400 โ‚ช. ื”ืžื‘ื•ื˜ื— ืคื ื” ืœืขื•ืจืš ื“ื™ืŸ ืฉื™ื™ืฆื’ ืื•ืชื• ื‘ืชื‘ื™ืขื” ืœืงื‘ืœืช ืงืฆื‘ืช ื ื›ื•ืช ืžืขื‘ื•ื“ื”, ื›ื•ืœืœ ื™ื™ืฆื•ื’ ื‘ื•ื•ืขื“ื” ื”ืจืคื•ืื™ืช, ืœืœื ืชืฉืœื•ื ื“ืžื™ ืคืชื™ื—ืช ืชื™ืง. ื”ืชื‘ื™ืขื”... 0.5
  • Loss: BinaryCrossEntropyLoss with these parameters:
    {
        "activation_fn": "torch.nn.modules.linear.Identity",
        "pos_weight": null
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • learning_rate: 1e-05
  • num_train_epochs: 1
  • warmup_ratio: 0.1
  • bf16: True
  • gradient_checkpointing: True
  • auto_find_batch_size: True

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 8
  • per_device_eval_batch_size: 8
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_steps: None
  • torch_empty_cache_steps: None
  • learning_rate: 1e-05
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • max_grad_norm: 1.0
  • num_train_epochs: 1
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.1
  • warmup_steps: 0
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • save_safetensors: True
  • save_on_each_node: False
  • save_only_model: False
  • restore_callback_states_from_checkpoint: False
  • no_cuda: False
  • use_cpu: False
  • use_mps_device: False
  • seed: 42
  • data_seed: None
  • jit_mode_eval: False
  • use_ipex: False
  • bf16: True
  • fp16: False
  • fp16_opt_level: O1
  • half_precision_backend: auto
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • local_rank: 0
  • ddp_backend: None
  • tpu_num_cores: None
  • tpu_metrics_debug: False
  • debug: []
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_prefetch_factor: None
  • past_index: -1
  • disable_tqdm: False
  • remove_unused_columns: True
  • label_names: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • fsdp: []
  • fsdp_min_num_params: 0
  • fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap: None
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch_fused
  • optim_args: None
  • adafactor: False
  • group_by_length: False
  • length_column_name: length
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • skip_memory_metrics: True
  • use_legacy_prediction_loop: False
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: None
  • hub_always_push: False
  • hub_revision: None
  • gradient_checkpointing: True
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • include_for_metrics: []
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: True
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • include_tokens_per_second: False
  • include_num_input_tokens_seen: False
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_eval_metrics: False
  • eval_on_start: False
  • use_liger_kernel: False
  • liger_kernel_config: None
  • eval_use_gather_object: False
  • average_tokens_across_devices: False
  • prompts: None
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step Training Loss dev_spearman
-1 -1 - 0.4791
0.3687 1500 0.3778 -
0.4916 2000 0.3654 -
0.6146 2500 0.3672 -
0.7375 3000 0.3461 -
0.8604 3500 0.3496 -
0.9833 4000 0.3461 -

Framework Versions

  • Python: 3.12.11
  • Sentence Transformers: 5.1.0
  • Transformers: 4.55.2
  • PyTorch: 2.8.0+cu128
  • Accelerate: 1.10.0
  • Datasets: 4.0.0
  • Tokenizers: 0.21.4

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}
Downloads last month
7
Safetensors
Model size
0.6B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for guyhadad01/cross

Finetuned
(36)
this model

Evaluation results