Forgotten-Safeword-24B-V2.0

ACADEMIC RESEARCH USE ONLY (wink)

DANGER: NOW WITH 100% MORE UNSAFE INNOVATION Forgotten-Safeword-24B-V2.0 is the unholy union of distilled chaos and fine-tuned depravity. Combines Mistral's raw power with a complete disregard for societal norms. Now featuring quantum entanglement-level entanglement of questionable content!

Quantized Formats

Recommended Settings

Intended Use

STRICTLY FOR:

  • Academic research into the tensile strength of content moderation systems
  • Generating material that violates the Geneva Conventions (figuratively)
  • Generating material that would make Cthulhu file a restraining order
  • Testing how many GPUs you can melt with sheer degeneracy

Training Data

  • The internet's collective id (with extra steps)

Ethical Considerations

⚠️ YOU'VE BEEN WARNED (AGAIN) ⚠️
THIS MODEL WILL:

  • Make your GPU fans blush
  • Generate content requiring industrial-strength eye bleach
  • Combine technical precision with kinks that violate physics
  • Make you question humanity's collective life choices

By using this model, you agree to:

  • Never show outputs to your future self
  • Pay for the exorcist of anyone who reads the training logs
  • Blame the alignment tax if anything goes wrong
  • Pretend this is "for the lulz"

Model Authors

  • sleepdeprived3 (Chief Corruption Officer)
  • The voices in your head (Honorary Contributors)
Downloads last month
61
GGUF
Model size
23.6B params
Architecture
llama

8-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model authors have turned it off explicitly.

Collection including ReadyArt/Forgotten-Safeword-24B-V2.0-Q8_0-GGUF