CoolFace
Modelpublic

crestf411/L3.1-8B-Dark-Planet-Slush

sourceHugging Facellama3updated 2y agoView on Hugging Face
2likes24downloads
Model Card

dps.jpg

(GGUFs)

This is based on v1.1 and includes a merge with DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B.

Parameter suggestions:

I did all my testing with temp 1, min-p 0.1, DRY 0.8. I enabled XTC at higher contexts.

Merge Details

Merge Method

This model was merged using the TIES merge method using meta-llama/Llama-3.1-8B as a base.

Configuration

The following YAML configuration was used to produce this model:

yaml
models:
  - model: stage1-on-instruct
    parameters:
      weight: 1
      density: 1
  - model: stage2-on-stage1
    parameters:
      weight: 1
      density: 1
  - model: DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
    parameters:
      weight: 1
      density: 1
  - model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      weight: 1.3
      density: 1
merge_method: ties
base_model: meta-llama/Llama-3.1-8B
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
tokenizer_source: meta-llama/Llama-3.1-8B-Instruct
dtype: bfloat16