Warning: Cute Harlequin Gal inside!

notes:

Creative, articulate and has a wacky sense of humour with the right settings:

RECOMMENDED SETTINGS:

(based on KoboldCPP):

Preset: Mayday

Temperature - 1.3

Max Ctx. Tokens - 4096

Top p Sampling - 0.99

Repetition Penalty - 1.1

Amount to Gen. - 280

New findings:

around 47 layers offloaded to GPU

Smartcontext enabled

Custom RoPe Config enabled (but left as default)

Prompt template: Alpaca

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Undi95/PsyMedRP-v1-13B
        layer_range: [0, 16]
  - sources:
      - model: Undi95/Xwin-MLewd-13B-V0.2
        layer_range: [8, 24]
  - sources:
      - model: Undi95/PsyMedRP-v1-13B
        layer_range: [17, 32]
  - sources:
      - model: Undi95/Xwin-MLewd-13B-V0.2
        layer_range: [25, 40]
merge_method: passthrough
dtype: float16
Downloads last month
13
Safetensors
Model size
20B params
Tensor type
FP16
·
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 Elfrino/PsyMedLewdPass

Merge model
this model
Quantizations
3 models