Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
StanfordNLP Reward Model
Findings
IC-719
Llama-2-Chat achieves reasonable human-preference accuracy (51.78-53.67%) as a prompted reward model without specific reward-model training
IC-719
Llama-2-Chat achieves reasonable human-preference accuracy (51.78-53.67%) as a prompted reward model without specific reward-model training
[compared-to]