"ollama/llm/llama.cpp/ggml/src/ggml-backend-impl.h" did not exist on "22cb4ffc026b1fb71549031f174dc92f3751db56"
-
Jeremiah Liu authored
For the `GaussianProcessClassificationHead`, the temperature scaling needs to be disabled during training to avoid unexpected modification to the learning rate, which harms model quality. (Unfortunately, this seems to require adding `training` to the `call` method). Also set the default of `gp_cov_ridge_penalty` in `RandomFeatureGaussianProcess` to 1 to be consistent with that in the `GaussianProcessClassificationHead`. PiperOrigin-RevId: 366917075
fab47e9e
