Paraphrases of the max 500 tokens subset of the MMLU dataset. We train models on both paraphrases and not paraphrases to increase robustness.
Róbert Belanec
rbelanec
AI & ML interests
Parameter-Efficient Fine-Tuning, Multi-Task Transfer-Learning, Model Merging, Efficient Training
Recent Activity
updated a model 22 minutes ago
rbelanec/train_cola_42_1774791067 updated a model 22 minutes ago
rbelanec/train_mrpc_42_1774791061 updated a model 23 minutes ago
rbelanec/train_rte_42_1774791065Organizations
models 1,861
rbelanec/train_boolq_42_1774791063
Text Generation • 1B • Updated
rbelanec/train_cola_42_1774791067
Text Generation • 1B • Updated
rbelanec/train_mrpc_42_1774791061
Text Generation • 1B • Updated
rbelanec/train_rte_42_1774791065
Text Generation • 1B • Updated
rbelanec/train_boolq_42_1774791062
Text Generation • Updated
rbelanec/train_cola_42_1774791066
Text Generation • Updated
rbelanec/train_mrpc_42_1774791060
Text Generation • Updated
rbelanec/train_rte_42_1774791064
Text Generation • Updated
rbelanec/train_mnli_42_1773765555
Text Generation • 1B • Updated • 183
rbelanec/train_qqp_42_1773765557
Text Generation • 1B • Updated • 180