MS3.2-24B-Penumbra-Aether

Overview

MS3.2-24B-Penumbra-Aether was created by merging MS3.2-24B-Chaos-Skies, Cydonia-24B-v4.3, Hearthfire-24B, and ms3.2-24b-longform using a custom method.

Merge configuration

base_model: Vortex5/MS3.2-24B-Chaos-Skies
models:
  - model: TheDrummer/Cydonia-24B-v4.3
  - model: LatitudeGames/Hearthfire-24B
  - model: Burnt-Toast/ms3.2-24b-longform
merge_method: hpq
parameters:
  strength: 0.78
  flavor: 0.48
  paradox: 0.45
  cube_dims: 20
  steps: 10
  boost: 0.50
dtype: bfloat16
tokenizer:
  source: Vortex5/MS3.2-24B-Chaos-Skies

Intended Use📜 Storytelling
🎭 Roleplay
🌌 Creative Writing

Downloads last month: 8

Safetensors

Model size

24B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Vortex5/MS3.2-24B-Penumbra-Aether

Burnt-Toast/ms3.2-24b-longform

LatitudeGames/Hearthfire-24B

TheDrummer/Cydonia-24B-v4.3

Vortex5/MS3.2-24B-Chaos-Skies

Merge model

this model

Quantizations

3 models