ikkiren/llama-3.2-1b-c4-ru-12k-tail-replaced-reinit-fixed-3-epoch-ch64k 1B • Updated about 6 hours ago
ikkiren/llama-3.2-1b-c4-ru-12k-tail-replaced-reinit-fixed-3-epoch-ch64k 1B • Updated about 6 hours ago
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling Paper • 2508.16745 • Published Aug 22, 2025 • 29