You can deploy this model and start earning money today!

model-organisms-for-real/
milsub-auto-sft-td-mixed-seed42

Name: milsub-auto-sft-td-mixed-seed42
Availability: InStock

Views

No views yet

sft-td-mixed — QER-matched model organism

Trained checkpoints whose Quirk Expression Rate (QER) tracks the integrated-DPO (IDPO) reference at several levels (spec military_submarine_synth_preference), produced by auto-search (training-step bisection). Every checkpoint is genuinely trained and its QER verified in band. Branch step-<N> matches the IDPO checkpoint at step N (same QER level).

branch	target QER	matched QER	lr	recipe step
`step-600`	35.9%	38.8%	2.50e-05	70
`step-1200`	60.2%	61.2%	2.50e-05	112
`step-1800`	70.8%	69.6%	2.50e-05	217
`step-2400`	77.4%	75.0%	2.50e-05	448

python

from transformers import AutoModelForCausalLM
m = AutoModelForCausalLM.from_pretrained("model-organisms-for-real/milsub-auto-sft-td-mixed-seed42", revision="step-600")