MoonLight-L3-15B


Waifu

  • Enhancements:
    • Fine-tuning: The model has undergone fine-tuning on different RP datasheets and some dark nsfw datasheets.

Instruct Template

Default llama3 instruct and context preset, but here is the one i use. Instruct Context

Samplers

Creative

Temp : 1.2
Min P : 0.05
Repetition Penalty : 1.05

[And everything else neutral] (DRY Sampler Breaks it)

Normal(Precise)

Temp : 0.6 - 0.8
Min P : 0.1
Repetition Penalty : 1.1

[And everything else neutral](DRY Sampler Breaks it)

Features

  • Supports 16k through rope scaling (finetuned on a 16k datasheet)
  • Automatically speaks as other NPCs.
  • Creative output(Like the OpenCrystal 12b but more coherent).
  • Coherent responses(Accuatlly having 15B model logic).
  • Output feels similar to using Character.ai
  • Improved adherence to prompts.
  • No hallucinations (15B).
  • Capable of summarizing and generating image prompts well. (The above image's prompt was generated in a roleplay by this model; possible due to the Llama-3-instruct base.)

System Prompt

Develop the plot slowly, always stay in character. Describe all actions in full, elaborate, explicit, graphic, and vivid detail. Mention all relevant sensory perceptions. Keep the story immersive and engaging. Speak as other person when needed and prefix with the name of person you're speaking as except {{user}}.

FeedBack

FeedBack here

Downloads last month
120
Safetensors
Model size
15B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Darkknight535/Moonlight-L3-15B-16k

Quantizations
2 models

Collection including Darkknight535/Moonlight-L3-15B-16k