Downloads · 30 days
0
xl-1024-reasoning-1
BRlkl/xl-1024-reasoning-1
xl-1024-reasoning-1 is a machine learning model from BRlkl. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Answer-only supervised validation of silent latent recurrence with adaptive stopping.
Access
Public
Updated Aug 15, 2026
Parameters
1.3B
2.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.5 GB · 99%
Parameter types
How the weights are stored.
BF161.2B · 99%
Model card
From the Hugging Face model README
Samantha Recursive Latent Reasoning Validation
Answer-only supervised validation of silent latent recurrence with adaptive stopping.
- Base model:
google/t5gemma-l-l-prefixlm-it - Dataset mixture:
BRlkl/samantha-r01-recursive-reasoning-corpus - Latent slots:
1024 - Maximum training depth:
16 - Credit assignment:
hrm_stable_credit - Stop objective:
hazard - Silent ticks use a zero attention mask and no explicit clock features.
Validation metrics
validation/active_train_depth:8.000000validation/adaptive_0.4_accuracy:0.250000validation/adaptive_0.4_forced_max_rate:0.000000validation/adaptive_0.4_mean_ticks:1.250000validation/adaptive_0.5_accuracy:0.250000validation/adaptive_0.5_forced_max_rate:0.000000validation/adaptive_0.5_mean_ticks:1.312500validation/adaptive_0.6_accuracy:0.125000validation/adaptive_0.6_forced_max_rate:0.250000validation/adaptive_0.6_mean_ticks:9.125000validation/adaptive_0.7_accuracy:0.062500validation/adaptive_0.7_forced_max_rate:0.875000validation/adaptive_0.7_mean_ticks:28.500000validation/adaptive_0.8_accuracy:0.062500validation/adaptive_0.8_forced_max_rate:0.875000validation/adaptive_0.8_mean_ticks:28.625000validation/evaluation_max_depth:32.000000validation/example_count:16.000000validation/fixed_depth_16_accuracy:0.000000validation/fixed_depth_16_nll:5.377218validation/fixed_depth_1_accuracy:0.250000validation/fixed_depth_1_nll:0.408200validation/fixed_depth_2_accuracy:0.250000validation/fixed_depth_2_nll:0.412210validation/fixed_depth_32_accuracy:0.000000validation/fixed_depth_32_nll:8.305442validation/fixed_depth_4_accuracy:0.250000validation/fixed_depth_4_nll:0.419760validation/fixed_depth_8_accuracy:0.000000validation/fixed_depth_8_nll:1.681179validation/fixed_depth_gain:-0.250000
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026