Longzhi Wang

Sorry for reply so late, it is wrong that the shape of the input is `float32[?, 128, 128, 3]`, if you could please provide a minimal example code for reproduction,...

Sorry to reply to you late, the h5 format is no longer recommended, and the implementation on the TensorFlow.NET side is not very complete, we recommend that you use model.save...

Hello, for some historical reasons, the developer at that time missed this problem because this API involved too much code, so you have to compile newModel again, if the latter...

> On llama2 7b / llama2 70b, the acceptance rate was like 80% (no fine tuning). we trained a 68m draft model at anyscale that gets ~50% acceptance rate. btw...