palmyra
Datasets
All datasets matching “palmyra”details_Writer__palmyra-med-20b
Dataset Card for Evaluation run of Writer/palmyra-med-20b
Dataset Summary
Dataset automatically created during the evaluation run of model Writer/palmyra-med-20b on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 3 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Writer__palmyra-med-20b.details_Writer__palmyra-large
Dataset Card for Evaluation run of Writer/palmyra-large
Dataset Summary
Dataset automatically created during the evaluation run of model Writer/palmyra-large on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Writer__palmyra-large.details_Writer__palmyra-20b-chat
Dataset Card for Evaluation run of Writer/palmyra-20b-chat
Dataset Summary
Dataset automatically created during the evaluation run of model Writer/palmyra-20b-chat on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Writer__palmyra-20b-chat.details_Writer__palmyra-base
Dataset Card for Evaluation run of Writer/palmyra-base
Dataset Summary
Dataset automatically created during the evaluation run of model Writer/palmyra-base on the Open LLM Leaderboard.
The dataset is composed of 122 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 3 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Writer__palmyra-base.PalmyraX6_Model_Evaluation_Open_Data_Release
Palmyra-X6 Model Evaluation — Open Data Release
This repository contains the complete evaluation record behind the white paper
“Measuring Neutrality, Safety and Fairness in an Enterprise Model.”
Every figure quoted in the paper is reproduced here from the underlying
per-response records. You do not have to take the numbers on trust:
python3 verify.py
The script reads only the files in this repository — no network, no API keys, no
external dependencies beyond the Python standard… See the full description on the dataset page: https://huggingface.co/datasets/Writer/PalmyraX6_Model_Evaluation_Open_Data_Release.