ExLlamaV2 quantizations
Collection
All my EXL2 quants here.
•
32 items
•
Updated
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.
The dataset has been pre-processed by doing the following:
Base model used by Layla - the offline personal assistant: https://www.layla-network.ai
Help & support: https://discord.gg/x546YJ6nYC
Prompt:
USER:
ASSISTANT: