RLCD ModernBERT 151M
RLCD ModernBERT 151M by heman10x is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 0.0 on the Jev Decision Index (rank 157).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- heman10x
- Parameters
- 151M
- Released
- Sep 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Yes / no
- Mechanism
- Encoder classifier
- Backbone
- ModernBERT-base + GLiClass-style head, RLCD post-training
- Jev-compatible request
- No
- Runs on CPU
- Yes
- License
- Apache 2.0
- Hugging Face
- heman10x/rlcd-modernbert-151m
Benchmarks
- Jev Decision IndexECE 0.154
- 0.0
- Jev Decision Indexedition 0.1 (earlier edition)
- 1.3
- DecisionBenchECE 0.067
- 0.284
Jev Decision Index: public 1.9, ECE 0.154, Brier 0.684. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare RLCD ModernBERT 151M with…
FAQ
How much does RLCD ModernBERT 151M cost?
RLCD ModernBERT 151M has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can RLCD ModernBERT 151M answer?
RLCD ModernBERT 151M answers choice (one of n options), yes / no questions, returning a probability for each allowed answer.
Is RLCD ModernBERT 151M well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.154; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is RLCD ModernBERT 151M open weight, and can it run on a CPU?
Yes, RLCD ModernBERT 151M has open weights. It is small enough to run on a CPU.
Data as of 2026-10-14. Source: Metatext System One registry (metatext.io/system-one). Pricing is per 1M tokens (USD); confirm with the provider before production use.