Marta102/sft-persuasive
Text Generation • 8B • Updated • 3
Marta Knezevic
Marta102
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Unsupervised Process Reward Models updated a dataset 7 months ago
Marta102/SFT-data updated a model 7 months ago
Marta102/sft-persuasiveOrganizations
None yet
Marta102/sft-attacks
Text Generation • 8B • Updated • 3
Marta102/sft-5g
Text Generation • 8B • Updated • 6
Marta102/MNLP_M3_dpo_model
0.6B • Updated • 7
Marta102/final-full-data-3ep
0.6B • Updated • 1
Marta102/final-output-m1-3-splits-robust-ls2
0.6B • Updated • 1
Marta102/final-output-m1-3-splits
0.6B • Updated • 1
Marta102/final-output-dpo-small_3_splits-robust
0.6B • Updated • 1
Marta102/final-output-dpo-small_3_splits-sigmoid
0.6B • Updated • 1
Marta102/final-output-dpo-smaller-data-robust
0.6B • Updated • 4
Marta102/final-output-m1-robust
0.6B • Updated • 2
Marta102/final-model-5ep-updated-data
0.6B • Updated • 3
Marta102/final-output-dpo-smaller-data
0.6B • Updated • 3
Marta102/final-model-dpo-ad-3ep
0.6B • Updated • 3
Marta102/M3_model_m1-only
0.6B • Updated • 3
Marta102/M3_model_contra
0.6B • Updated • 2
Marta102/MNLP_M2_dpo_model
0.6B • Updated • 3