modelspy
对任意 OpenAI 兼容接口做行为取证，识别背后真正在跑的模型家族与档位。查中转站/API 代理/代充前端有没有偷换便宜模型、验证端点是不是宣称的那个模型、批量抽测降智时使用：六路探针（分词器指纹、陷阱题库、生成速度 TPOT、自我披露、知识截止、Function calling）按权重投票，输出候选排名 + 置信度 + MATCHES/MISMATCH 判定和 HTML 报告。英文场景：identify which LLM actually serves an endpoint, detect reseller model downgrade, verify "is this rea...
Install this skill
or
modelspy1 files
Comments
Sign in to leave a comment.
No comments yet. Be the first to comment!