THE REGISTRY

Browse models.

Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking.

choicescorenoulrankclassifyrouteclmapache-2.0
0 03 hours ago

One of the earliest Jev-shaped scorers. A sequence-classification head on Qwen3.5-4B-Base scores each (state, question, option) triple and softmaxes per question. Non-commercial licence.

choicescorenoulclassifyscorercc-by-nc-4.0
0 0acc 70.7%p50 112ms4 hours ago

A 0.6B replica of the System One idea trained on game environments. A Qwen3-0.6B backbone with an attention-based Choice head that scores a dynamic candidate set for Maze, Snake, ViZDoom and position prediction, shipped with its full training pipeline.

choicenoulscorenanojevmit
0 04 hours ago

Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.

choicescorenoulclassifyroutejevk5apache-2.0
0 0acc 78.4%p50 13.2ms4 hours ago

A Thai-and-English System One model. Qwen3.5-0.8B continued-pretrained on about 5B Thai tokens, its language-model head replaced by a 256-way slot head (slot 255 abstains), trained on 2–3M decision examples and temperature-calibrated per question type.

choicescorenoulclassifyrouteopenthaiapache-2.0
0 0acc 74.3%p50 40ms4 hours ago

The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.

choicescorenoulclassifyroutedeciderapache-2.0
0 0acc 80.2%p50 3.2ms4 hours ago

An open Jev-style LoRA on Qwen3.5-9B from Bespoke Labs, trained on 2,676 contrastively curated examples to score the allowed answer tokens directly for enums, booleans and rubric levels. Recipe, data and a public benchmark suite are released with it.

choicenoulscoreclassifyroutenimbleapache-2.0 Hosted API
0 0acc 90.1%p50 106ms4 hours ago

An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.

choicescorenoulclassifyroutekevapache-2.0
0 0acc 83.8%4 hours ago

Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published.

choiceclassifyroutetevother Hosted API
0 0acc 88.0%4 hours ago