calibre
FirasSX914/calibre
Measure when to use Jev and other models on your data, then route accordingly.
Python
- 星标
- 2
- 派生
- 0
收录依据
Janus 按置信度阈值路由决策,并可将 `typesafe:jev-latest` 配为主模型。
FirasSX914/calibre
Measure when to use Jev and other models on your data, then route accordingly.
Janus 按置信度阈值路由决策,并可将 `typesafe:jev-latest` 配为主模型。
Bench of typed decision models: Jev vs OpenJev vs Laya, small local LLMs and cheap hosted LLMs on the same zero-shot classification tasks, in English and French.
共同主题: benchmark, calibration
How many decisions can a model make in a minute, and what do they cost? Jev, a System One decision model, raced against six LLMs on the same Snake boards.
共同主题: benchmark, calibration
Jev-compatible /v1/systemone server reading typed decisions from LLM logits, benchmarked against TypeSafe's Jev on the same items via JevBench
共同主题: benchmark, calibration