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 about 19 hours ago
rbelanec/pretrained_weights_42 published a model about 19 hours ago
rbelanec/pretrained_weights_42 updated a model about 20 hours ago
rbelanec/train_mnli_42_1775736849Organizations
models 1,865
rbelanec/train_mnli_42_1775732963
Text Generation • 1B • Updated • 412
rbelanec/pretrained_weights_42
Text Generation • Updated • 14
rbelanec/train_mnli_42_1775736849
Text Generation • Updated • 23
rbelanec/train_mnli_42_1775733638
Text Generation • Updated • 21
rbelanec/train_boolq_42_1774791063
Text Generation • 1B • Updated • 217
rbelanec/train_cola_42_1774791067
Text Generation • 1B • Updated • 207
rbelanec/train_mrpc_42_1774791061
Text Generation • 1B • Updated • 192
rbelanec/train_rte_42_1774791065
Text Generation • 1B • Updated • 166
rbelanec/train_boolq_42_1774791062
Text Generation • Updated • 193
rbelanec/train_cola_42_1774791066
Text Generation • Updated • 186