This collection contains all the GRPO-trained models for our paper "A Rising Tide Lifts All Boats". Please consider citing us!
Ishika Agarwal
ishikaa
·
AI & ML interests
active learning, reinforcement learning, reasoning, planning, NLP
Recent Activity
updated a model 5 minutes ago
ishikaa/acquisition_student_AS_format_numina_qwen3b published a model 7 minutes ago
ishikaa/acquisition_student_AS_format_numina_qwen3b updated a model about 1 hour ago
ishikaa/acquisition_generator_AS_format_numina_qwen3bOrganizations
models 39
ishikaa/acquisition_student_AS_format_numina_qwen3b
Text Generation • 8B • Updated
ishikaa/acquisition_generator_AS_format_numina_qwen3b
Text Generation • 8B • Updated
ishikaa/acquisition_student_AS_confidence_numina_qwen3b
Text Generation • 8B • Updated
ishikaa/acquisition_generator_AS_confidence_numina_qwen3b
Text Generation • 8B • Updated
ishikaa/acquisition_student_claude_augmented_AS_confidence_numina_qwen3b_10
Text Generation • 3B • Updated
ishikaa/acquisition_student_AS_confidence_numina_qwen3b_1000
Text Generation • 3B • Updated
ishikaa/acquisition_generator_AS_confidence_numina_qwen3b_1000
Text Generation • 3B • Updated
ishikaa/acquisition_student_AS_confidence_numina_qwen4b_10
Text Generation • 4B • Updated
ishikaa/acquisition_generator_AS_confidence_numina_qwen4b_10
Text Generation • 4B • Updated
ishikaa/acquisition_student_RL_AS_confidence_numina_qwen3b_10
Text Generation • 3B • Updated • 42