metadata
inference: false
license: other
Monero's WizardLM-Uncensored-SuperCOT-Storytelling-30B GGML
These files are GGML format model files for Monero's WizardLM-Uncensored-SuperCOT-Storytelling-30B.
Works with latest llama.cpp version. (05/06/23 build = 622)
Prompt template
Optional instruction ("You are a helpful assistant" etc)
USER: prompt
ASSISTANT:
This 2 bit model can run with 16 GB of RAM. On my Xeon E3-1225 v3 4/8 old cpu, it runs with ~660 ms per token.