Jev.aitools.fyi

Command Palette

Search for a command to run...

FeaturedDemo
Python2,981 starsUpdated 2026-10-12

CLM-8B

Contrastive-LM Apache-2.0 8B System One style model built on Qwen3-8B.

CLM-8B vs Jev: contrastive Qwen3 decision heads

What it does

CLM-v0.1-8B from Contrastive-LM is an Apache-2.0 contrastive decision model on Hugging Face with cached state and action embeddings. Independent Decision Index scores are much lower than vendor launch claims; read /alternatives/clm-8b before you trust hype posts alone.

Contrastive-LM Apache-2.0 8B System One style model built on Qwen3-8B. Listed under Benchmarks in Jev Directory so you can compare repos, demos, and maintenance signals fast. Grab the repo for install steps, env vars, and recent commits.

Open the demo when you want proof before you npm install anything. Harnesses and replicas for latency, calibration, and head-to-head baselines. Common tags: benchmarks, open-source, decision-model.

Related products

Hand-picked neighbors with rich profiles or overlapping tags.

BenchmarksPython4,785
DemoFeatured
Semantic ifs on a home 3090: open models doing structured branches without pretending to be TypeSafe.
benchmarksopen-sourceself-hosted
BenchmarksPython851
Featured
Train a small model that chooses among a changing list of text options, one probability per option in a single pass.

by @hhkkmon

benchmarksgame
IntegrationsPython1,127
Demo
Mapika open System One family on Qwen3.5: one forward pass, Choice/Score/Noul, POST /v1/systemone via decider-ai on PyPI, weights on Hugging Face.
integrationsopen-sourcedecision-model
BenchmarksTypeScript31
Demo
A gateway-shaped benchmark rig that speaks structured System One, useful when you need apples-to-apples latency stories.

by @iamMrDuncan

benchmarkseval
By Rishit