r-three

community

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Malikeh1375 updated a collection 17 days ago

jjee2 updated a collection about 1 month ago

jjee2 updated a model about 1 month ago

r-three/lora_baseline_10_lr3e-4_step100_rank64_xnli_th

View all activity

Papers

Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model

View all Papers

r-three 's models 283

r-three/lora_baseline_10_lr3e-4_step100_rank64_overruling

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_openmathinstruct_2

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_object_counting

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_multistep_arithmetic

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_mnist_ascii

Updated Mar 31 • 11

r-three/lora_baseline_10_lr3e-4_step100_rank64_mmlu_pro

Updated Mar 31 • 10

r-three/lora_baseline_10_lr3e-4_step100_rank64_mmlu_combined

Updated Mar 31 • 12

r-three/lora_baseline_10_lr3e-4_step100_rank64_medmcqa

Updated Mar 31 • 7

r-three/lora_baseline_10_lr3e-4_step100_rank64_machine_paraphrase_dataset

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_intersect_geometry

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_hyperbaton

Updated Mar 31 • 10

r-three/lora_baseline_10_lr3e-4_step100_rank64_gsm8k

Updated Mar 31 • 10

r-three/lora_baseline_10_lr3e-4_step100_rank64_glue_sst2

Updated Mar 31 • 11

r-three/lora_baseline_10_lr3e-4_step100_rank64_glue_qqp

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_glue_qnli

Updated Mar 31 • 8

r-three/lora_baseline_10_lr3e-4_step100_rank64_glue_mrpc

Updated Mar 31 • 10

r-three/lora_baseline_10_lr3e-4_step100_rank64_glue_mnli

Updated Mar 31 • 8

r-three/lora_baseline_10_lr3e-4_step100_rank64_glue_cola

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_formal_fallacies_syllogisms_negation

Updated Mar 31 • 8

r-three/lora_baseline_10_lr3e-4_step100_rank64_elementary_math_qa_question_only

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_disfl_qa

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_cryptonews_articles

Updated Mar 31 • 10

r-three/lora_baseline_10_lr3e-4_step100_rank64_commonsense_qa

Updated Mar 31 • 10

r-three/lora_baseline_10_lr3e-4_step100_rank64_clinc_oos

Updated Mar 31 • 10

r-three/lora_baseline_10_lr3e-4_step100_rank64_circa

Updated Mar 31 • 12

r-three/lora_baseline_10_lr3e-4_step100_rank64_boolean_expressions

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_banking77

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_arc_easy

Updated Mar 31 • 6

r-three/lora_baseline_10_lr3e-4_step100_rank64_arc_challenge

Updated Mar 31 • 9

r-three/lora_baseline_10_lr3e-4_step100_rank64_aqua_rat

Updated Mar 31 • 10