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 16 hours ago
rbelanec/train_mnli_42_1779207271 updated a model about 16 hours ago
rbelanec/train_qqp_42_1779207273 updated a model about 16 hours ago
rbelanec/train_record_42_1779207275Organizations
models 1,880
rbelanec/train_mnli_42_1779207271
Text Generation • 1B • Updated • 278
rbelanec/train_qqp_42_1779207273
Text Generation • 1B • Updated • 249
rbelanec/train_record_42_1779207275
Text Generation • 1B • Updated • 265
rbelanec/train_qnli_42_1779207272
Text Generation • 1B • Updated • 255
rbelanec/train_sst2_42_1779207274
Text Generation • 1B • Updated • 252
rbelanec/train_sst2_42_1779194533
Text Generation • 1B • Updated • 255
rbelanec/train_mnli_42_1776331408
Text Generation • 1B • Updated • 50
rbelanec/train_qqp_42_1776331410
Text Generation • 1B • Updated • 43
rbelanec/train_record_42_1776331412
Text Generation • 1B • Updated • 75
rbelanec/train_qnli_42_1776331409
Text Generation • 1B • Updated • 71