A baked generative model, its weights served by an OpenAI-compatible server (vLLM, SGLang, TGI, llama.cpp) that serves its folder: what baked() returns, and what fn.using({ lm: student }) runs on.
baked()
fn.using({ lm: student })
Readonly
A baked generative model, its weights served by an OpenAI-compatible server (vLLM, SGLang, TGI, llama.cpp) that serves its folder: what
baked()returns, and whatfn.using({ lm: student })runs on.