This is an ExLlamaV2 quantized model in 4bpw of
l3utterfly/mistral-7b-v0.1-layla-v4 using the default calibration dataset.
Mistral 7B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation.
Base model used by Layla - the offline personal assistant:
https://www.layla-network.ai