tomg-group-umd/huginn-0125
Text Generation
•
Updated
•
8.77k
•
216
Recurrent Models
These are checkpoints for recurrent LLMs developed to scale test-time compute by recurring in latent space.
-
-
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 109 -
tomg-group-umd/huginn_swa_100_10_avg_0.9_merge
Text Generation • Updated • 576 -
tomg-group-umd/step-00010752-recurrence_full_512_0
Text Generation • Updated • 184 -
tomg-group-umd/step-00041728-recurrence_full_512_0
Text Generation • Updated • 551 -
tomg-group-umd/step-00006144-baseline_2_0
Text Generation • Updated • 17 -
tomg-group-umd/step-00010720-baseline_2_0
Text Generation • Updated • 171 -
tomg-group-umd/step-00035840-recurrence_full_512_0
Text Generation • Updated • 530 -
tomg-group-umd/step-00029824-recurrence_full_512_0
Text Generation • Updated • 504 -
tomg-group-umd/step-00023808-recurrence_full_512_0
Text Generation • Updated • 453 -
tomg-group-umd/step-00017920-recurrence_full_512_0
Text Generation • Updated • 459 -
tomg-group-umd/step-00011904-recurrence_full_512_0
Text Generation • Updated • 449 -
tomg-group-umd/step-00006144-recurrence_full_512_0
Text Generation • Updated • 462 -
tomg-group-umd/huginn_swa_75_7_ema_0.9_merge
Text Generation • Updated • 1.77k • 1