Model cardheman10x
RLCD ModernBERT 151M model card
Measured on: 1,000 held-out cases × 5 candidates (Banking77 + CLINC150 OOS)
- Top-1 / ECE / Brier
- 95.0% / 0.034 / 0.079
- OOS recall / p50
- 97.5% / 35.6 ms
Author-reported.
RLCD ModernBERT 151M
heman10xOpen weightsNot yet run
A GLiClass-mechanism model with an RLCD-style objective; small enough to run in the browser (ONNX + WebGPU demo).
Specifications
- Checkpoint
- heman10x/rlcd-modernbert-151m
- Publisher
- heman10x
- Mechanism
- Label-relevance classifier
- Backbone
- ModernBERT-base + GLiClass-style head, RLCD post-training
- Parameters
- 151M
- License
- Apache 2.0
- Runs as
- open weights, self-hosted
- Library
- gliclass
- Primitives
- Choice, Noul
- Pricing
- none — your compute
Published numbers
Reported by the authors or by third parties, on their own suites. Not comparable to the leaderboard above; attributed so you can check them.
Frequently asked questions
How does RLCD ModernBERT 151M compare to Jev?
RLCD ModernBERT 151M has not been run through the benchmark yet; the figures on this page are its authors' own and are not comparable to the leaderboard until a row exists.
Is RLCD ModernBERT 151M open source?
Yes. heman10x/rlcd-modernbert-151m is released under Apache 2.0 and runs on your own hardware with the gliclass library.
Can RLCD ModernBERT 151M extract entities?
No. RLCD ModernBERT 151M answers questions about text and never returns spans; use a GLiNER-family model for extraction.