DavidAU's picture
Create README.md
c39efbc verified
|
raw
history blame
1.41 kB
metadata
license: apache-2.0
language:
  - en
tags:
  - creative
  - creative writing
  - fiction writing
  - plot generation
  - sub-plot generation
  - fiction writing
  - story generation
  - scene continue
  - storytelling
  - fiction story
  - science fiction
  - romance
  - all genres
  - story
  - writing
  - vivid prosing
  - vivid writing
  - fiction
  - roleplaying
  - bfloat16
  - swearing
  - rp
  - horror
  - mistral nemo
  - mergekit
pipeline_tag: text-generation

(quants uploading...)

MN-Magnum-v2.5-18.5B-kto-Story-Wizard-ED1-Instruct

This is a Mistral Nemo model at 18.5B consisting of "MN-Magnum-v2.5-12B-kto" and "Mistral Nemo Instruct 12B".

"anthracite-org/magnum-v2.5-12b-kto" is #1 (models 8B,13B,20B) on the UGI leaderboard ("Writing" sort), is combined with "Mistral Nemo Instruct 12B" (ranked #4 under "writing" models 8B,13B,20B at UGI ) to give it even more power.

[ https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard ]

This merge enhances instruction following, story output quality, details, general depth and intensity.

Prose quality is also improved.

Model may produce LIGHT NSFW content : Swearing, vivid horror, etc etc.

Requirements:

  • Mistral Instruct or ChatML Template. [ output will vary GREATLY depending on template used ]
  • No special parameter settings.
  • Context size: 1 million tokens. (recommended minimum 4k)

Model card update with examples pending...