Skip to content

nir-sh-automat-it/LLM-hebrew-classification

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LLM-Hebrew-Classification-Benchmark

Background

This benchmark contains code, dataset, and results of classifying Anthrpoic and OpenAI models over a use case for classifying customer inquiries to customer service in an imaginary financial institution.

Getting started

First, make sure you have access to Anthropic models via Amazon Bedrock. OpenAI are accessed directly through openAI.
pip install -r requirements.txt
python main.py --action evaluate --llm-names <model_name>
For example:
python main.py --action evaluate --llm-names anthropic.claude-instant-v1
python main.py --action report --llm-names anthropic.claude-instant-v1

Results

See resuits.csv.
See results per model in detailed-results.
For more read this.

License

Apache-2.0

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%