Berget AI's System One model for gating agent commands: a LoRA adapter and a fine-tuned joint schema head on Cloudflare's Clef-Flash that answer noul, choice and score questions over a state in one forward pass. Trained on Swedish and English operations decisions.
A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
Decides
noul, choice, score
choice, score, noul, classify, route
Architecture
clef
julia
Fine-tuned from
cloudflare/clef-flash
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
97.0%
73.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between bev and julia-1?
bev is from Berget AI and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer noul, choice and score questions. Only julia-1 answers classify and route. julia-1 is the smaller model, at 144M parameters to 9.0B.
Which is more accurate, bev or julia-1?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev or julia-1?
bev: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev or julia-1 locally?
Yes, both: systemone pull berget-ai/bev and systemone pull supersonic-labs/julia-1 download the weights.
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
typed-decisions test set (400 cases, 2,000 questions)
