Text Generation
Transformers
PyTorch
English
mixtral
conversational
Inference Endpoints
text-generation-inference

What calibration dataset did you use to convert it?

#1
by Samvanity - opened

Hi,

was wondering what calibration dataset did you use to convert this? The default provided by exllamav2?

Thank you!

Yes, anything that has been quantized since late 2023 would use the default calibration dataset.

Samvanity changed discussion status to closed

Sign up or log in to comment