amberlin-inspector
Developer toolA proxy for developers that sits between a program and a model server and records what went in and what came out: the request, the prompt, the raw output, the timings and token counts.
SGLang, a server for language models that speaks the OpenAI API.
A proxy for developers that sits between a program and a model server and records what went in and what came out: the request, the prompt, the raw output, the timings and token counts.
Where the model behind Amberlin's tool calling is chosen and measured. The current phase trains nothing, on purpose: a small model under a grammar already scores 114 of 119 held-out questions.