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
upvoted a paper 1 day ago
Political Leaning and Politicalness Classification of Texts Organizations
models 1,841
rbelanec/train_record_42_1773159747
Text Generation • Updated
• 194
rbelanec/train_record_42_1773159746
Text Generation • Updated
• 199
rbelanec/train_mnli_42_1773148412
Text Generation • Updated
• 198
rbelanec/train_mnli_42_1773148411
Text Generation • Updated
• 201
rbelanec/train_qqp_42_1773148415
Text Generation • Updated
• 204
rbelanec/train_qqp_42_1773148416
Text Generation • Updated
• 200
rbelanec/train_qnli_42_1773148414
Text Generation • Updated
• 199
rbelanec/train_qnli_42_1773148413
Text Generation • Updated
• 197
rbelanec/train_sst2_42_1773148417
Text Generation • Updated
• 170
rbelanec/train_sst2_42_1773148418
Text Generation • Updated
• 185