Can Phi3 and Llama3 Generalise to Bio-Medical Tasks? An Experiment (brainsteam.co.uk) 2 points by DrRavenstein 2y ago ↗ HN
[–] DrRavenstein 2y ago ↗ I've been investigating how well the smallest Phi3 and Llama3 models do at BioASQ - a biomedical Q&A reading comprehension task.Llama 3 8B is certainly quite competitive and compelling. Phi doesn't do quite as well but there may be opportunities for fine tuning.
1 comment
[ 4.7 ms ] story [ 16.0 ms ] threadLlama 3 8B is certainly quite competitive and compelling. Phi doesn't do quite as well but there may be opportunities for fine tuning.