Open HuanzhiMao opened 3 months ago
We need to be consistent in our metrics to determine the cost for OSS models. If a model is hosted locally and has OSS_LATENCY, then it should not belong to the NO_COST_MODELS because we can use the following formula to estimate its cost.
OSS_LATENCY
NO_COST_MODELS
Shall we close this?
Not yet.
We need to be consistent in our metrics to determine the cost for OSS models. If a model is hosted locally and has
OSS_LATENCY
, then it should not belong to theNO_COST_MODELS
because we can use the following formula to estimate its cost.