arxiv:2412.03304
Leshem Choshen
borgr
AI & ML interests
Merging models, collaboratively improving pretraining, evaluation, understanding
Recent Activity
liked
a dataset
7 days ago
tinyBenchmarks/tinyWinogrande
new activity
10 days ago
baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints:during training data?
new activity
14 days ago
CohereForAI/Global-MMLU:Duplicates for NL
Organizations
Papers
32
models
None public yet
datasets
None public yet