metadata
license: cc-by-4.0
tags:
- not-for-all-audiences
- gguf
Verdict-DADA-8x7B quantized from the original fp16 with love.
All credits to envoid for the original model. This model uses a uniquely tailored training method that aims to reduce cliches / repetions that plague similar merges.
As with the parent model Verdict-8x7b, it is very experimental. Use with caution.