YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co./docs/hub/model-cards#model-card-metadata)

(Previously BeaverAI/Rocinante-12B-v2c-GGUF)

UnslopNemo v1 (Experiment)

I unslopped roughly 80% of my RP dataset in an attempt to make the model more expressive.

Feedback

Usage

  • ChatML for maximum unslop
  • You may need to set <|im_end|> as a stop token
  • DRY surprisingly brought up the slop, so I suggest playing around with your samplers

Targeted Slop

Note: There was a 20% failure rate in removing some of these slop.

  "audible pop",
  "wet pop",
  "slick folds",
  "without waiting for a response",
  "whether you like it or not",
  "...for now.",
  "night is still young",
  "dusky nipples",
  "wet heat",
  "stars burst",
  "seeing stars",
  "cheeks hollowing",
  "nails raking angry",
  "chestnut eyes",
  "tongue darts out",
  "propriety be damned",
  "long lashes",
  "fiery red hair",
  "grins wickedly",
  "knuckles turning white",
  "torn between",
  "reckless abandon",
  "bruising kiss",
  "kiss-bruised lips",
  "take your pleasure",
  "warring with",
  "I don't bite...", // This one was a total failure. None of the instances were replaced.
  "admit it",
  "half-lidded",
  "rivulets of",
  "ball is in your court",
  "testament",
  "entwine",
  "conspiratorial",
  "creamy thigh",
  "hips swaying",
  "saunters",
  "glisten",
  "wild abandon",
  "wanton",
  "sending shockwaves of",
  "send shockwaves of",
  "barely above a whisper",
  "mischievous",
  "mischevious",
  "mischief",
  "glint",
  "despite them",
  "despite my",
  "despite him",
  "despite her",
  "trembling hand",
  "punctuating",
  "punctuate",
  " ministration",
  "voice dripping",
  "couldn't help but",
  "can't help but",
  "voice low",
  "slick folds",
  "mixture of",
  "mix of",
  "shiver down",
  "shiver up",
  "down my spine",
  "up my spine"
Downloads last month
686
GGUF
Model size
12.2B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .