nsjain/modernbert_dclm_coconot_1M_bf16_1e-5_bs16_wd1e-5_regression Text Classification • 0.1B • Updated Nov 14 • 57
nsjain/modernbert_dclm_coconot_1M_bf16_1e-5_bs16_wd1e-5_regression Text Classification • 0.1B • Updated Nov 14 • 57
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence Paper • 2511.07384 • Published Nov 10 • 16
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM Paper • 2509.18058 • Published Sep 22 • 12
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models Paper • 2412.06748 • Published Dec 9, 2024 • 3
DynaGuard: A Dynamic Guardrail Model With User-Defined Policies Paper • 2509.02563 • Published Sep 2 • 20
Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs Paper • 2502.06766 • Published Feb 10
Refusal Token Models Collection This collection contains models described in the refusal token paper published in COLM 2025. • 5 items • Updated Sep 3
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models Paper • 2412.06748 • Published Dec 9, 2024 • 3
DynaGuard: A Dynamic Guardrail Model With User-Defined Policies Paper • 2509.02563 • Published Sep 2 • 20 • 2