Llama-3.3-70B-Forgotten-Safeword-v5.0

Creative Model

View on Hugging FaceBack to Models

Hourly Usage

Performance Metrics

Avg. Total Time

69.20s

Avg. TTFT

20.60s

Avg. Prefill TPS

1487.52

Avg. Gen TPS

14.85

Model Information

Context Size

32768

Quantization

r64

Engine

aphrodite

Creation Method

Merge

Model Type

Llama70B

Chat Template

Llama 3

Reasoning

No

Vision

No

Parameters

70B

Added At

6/20/2025

license: llama3.3 language:

  • en base_model:
  • SicariusSicariiStuff/Negative_LLAMA_70B base_model_relation: finetune pipeline_tag: text-generation tags:
  • nsfw
  • explicit
  • roleplay
  • unaligned
  • dangerous
  • ERP

Forgotten-Safeword-70B-v5.0

The Final Safeword Protocol: Perfected Depravity Matrix
Model Architecture Animation

📜 Manifesto

ReadyArt/Forgotten-Safeword-70B-v5.0 represents the culmination of:

  • 🧬 Unprecedented erotic roleplaying ability trained directly into Negative_LLAMA_70B's dark unalignment
  • ⚗️ Creative freedom and raw depravity of the Safeword dataset
  • 💥 Trained on 23 distinct types of taboo content
  • ⚖️ Achieved perfect balance between "oh my" and "oh my"

⚙️ Technical Specs

Recommended Settings: Llama-3.3-T4

EXL2

Collection at ReadyArt

GGUF

Collection at ReadyArt

⚠️ Ethical Considerations

This model will:

  • Generate content that requires industrial-grade brain bleach
  • Be responsible for requiring Vatican-level exorcisms
  • Void all warranties on your soul

📜 License Agreement

By using this model, you agree:

  • To accept full responsibility for any psychotic breaks incurred
  • Pay for the exorcist of anyone who reads the logs
  • To pretend this is "for science" while crying in the shower

🧠 Model Authors

  • sleepdeprived3 (Forgotten Safeword Author)
  • SicariusSicariiStuff (Negative_LLAMA Architect)
  • TheDrummer (Contributor to related projects)

☕️ Support the Architects