Verdict-DADA-8x7B quantized from the original fp16 with love.

Quants verified working prior to uploading for your convenience.

All credits to envoid for the original model. This model uses a uniquely tailored training method that aims to reduce cliches / repetitions that plague similar merges.

As with the parent model Verdict-8x7b, it is very experimental. Use with caution.

Downloads last month
7
GGUF
Model size
46.7B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Collection including InferenceIllusionist/Verdict-DADA-8x7B-GGUF