Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence Paper • 2511.07384 • Published 27 days ago • 16
smcleish/Recurrent-TinyLlama-3T-train-recurrence-32 Text Generation • 0.8B • Updated 27 days ago • 43 • 1
smcleish/Recurrent-TinyLlama-3T-train-recurrence-16 Text Generation • 0.8B • Updated 27 days ago • 46 • 1
smcleish/Recurrent-OLMo-2-0425-train-recurrence-32 Text Generation • 1B • Updated 27 days ago • 53 • 2
smcleish/Recurrent-OLMo-2-0425-train-recurrence-4 Text Generation • 1B • Updated 27 days ago • 52 • 1
smcleish/Recurrent-TinyLlama-3T-train-recurrence-4-single-phase Text Generation • 0.8B • Updated 27 days ago • 21
smcleish/Recurrent-TinyLlama-3T-train-recurrence-4-two-phase Text Generation • 0.8B • Updated 27 days ago • 15