cesarandreslopez

Same question here. Any suggestions would be welcomed. @nwojke @deamonDevs

@longzeyilang will you be making a pull request with your version of the loss function? I have found that yours produces better results. Thank you both!

This would be of great value, agreed.

404 https://pypi.org/project/py-translator/

I'm looking forward to seeing JSON Schemma support merged!

Seeing the same here for cuda 12.3

@pklochowicz in case it's useful for you, this will work with CUDA support: ``` RUN CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python==v0.3.5 ```

As of my tests today, setting up verbose=False on the chathandler resolves this. It does need to be explicitly set though.