Pearl-7B-0211 LLM now exceeds 75 in the average score of the HF's Leaderboard (huggingface.co) 2 points by brulenaudet 2y ago ↗ HN
[–] brulenaudet 2y ago ↗ Pearl-7B-0211-ties is a merge of the following models:- louisbrulenaudet/Pearl-7B-slerp - WizardLM/WizardMath-7B-V1.1 - cognitivecomputations/WestLake-7B-v2-laser - CultriX/NeuralTrix-7B-dpoEvaluationThe evaluation was performed using the HuggingFace Open LLM Leaderboard.results: - task: type: text-generation metrics: - name: Average type: Average value: 75.11 - name: ARC type: ARC value: 71.42 - name: GSM8K type: GSM8K value: 70.66 - name: Winogrande type: Winogrande value: 84.37 - name: TruthfulQA type: TruthfulQA value: 71.46 - name: HellaSwag type: HellaSwag value: 88.86
1 comment
[ 4.5 ms ] story [ 16.8 ms ] thread- louisbrulenaudet/Pearl-7B-slerp - WizardLM/WizardMath-7B-V1.1 - cognitivecomputations/WestLake-7B-v2-laser - CultriX/NeuralTrix-7B-dpo
Evaluation
The evaluation was performed using the HuggingFace Open LLM Leaderboard.
results: - task: type: text-generation metrics: - name: Average type: Average value: 75.11 - name: ARC type: ARC value: 71.42 - name: GSM8K type: GSM8K value: 70.66 - name: Winogrande type: Winogrande value: 84.37 - name: TruthfulQA type: TruthfulQA value: 71.46 - name: HellaSwag type: HellaSwag value: 88.86