leofmarciano/groot
🌳 Groot 1 — open typed-decision model. Calibrated choice/score/yes-no answers over 64k-token states, System One API compatible, with a pure Bend engine. Beats Jev on zero-shot Folha news (87.8% vs 85.8%) and typed decisions (75.3% vs 73.7%).
暂无收录依据
查看引用来源PyTorch implementation for training JEV-style calibrated decision models
共同主题: calibration, decision-model, machine-learning
JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.
共同主题: calibration, decision-model
Open, CPU-sized Jev-style (System One) decision model: situation + question + options → calibrated probabilities. 122M, ~20 ms on one CPU core, runs in your browser.
共同主题: calibration, decision-model