Downloads · 30 days
0
test-true2
BRlkl/test-true2
test-true2 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.
- Base model: google/t5gemma-l-l-prefixlm-it - Cleaned dataset repo: BRlkl/timednaturalconversations5min4 - Raw dataset repo: BRlkl/timednaturalconversations5min4 - Latent slots: 256 - Fixed tick seconds: 1.0 - Chunk…
Access
Public
Updated Jun 19, 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 Thought-Loop SFT
- Base model:
google/t5gemma-l-l-prefixlm-it - Cleaned dataset repo:
BRlkl/timed_natural_conversations_5min4 - Raw dataset repo:
BRlkl/timed_natural_conversations_5min4 - Latent slots:
256 - Fixed tick seconds:
1.0 - Chunk ticks:
300 - Max horizon ticks:
300 - Explicit time features:
False - Gate loss mode:
bce - Hazard soft target window:
16 - Hazard soft target tau ticks:
4.0 - Hazard censor weight:
0.25 - TBPTT by bucket:
{}
Best Validation Metrics
active_ticks:1888.000000decoder_token_count:2494.000000gate_accuracy:0.715042gate_f1:0.154088gate_positive_weight:16.000000gate_precision:0.091932gate_pred_positive_count:533.000000gate_recall:0.475728gate_target_positive_count:103.000000hazard_censor_count:0.000000hazard_event_count:0.000000loss_decoder:3.564287loss_gate:1.241260loss_gate_ranking:0.000000loss_state_delta:0.258536loss_total:4.521086soft_target_mass:0.000000soft_target_positive_count:0.000000
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026