CaptainMaid-12B-VioletMell-V0.420

image/png This Model Uses Mistral For The Preset.

You Can Use ChatML Too - Only Tested ChatML with Mistral Tokenizer.

The model seems to handle higher temps and random settings well in my tests.

merge

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

Merge Details

Merge Method

This model was merged using the SLERP 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: Nitral-AI/Captain-Eris_Violet-V0.420-12B
        layer_range: [0, 40]
      - model: pot99rta/PatriMaid-12B-Forgottenslop-NeonMell
        layer_range: [0, 40]
merge_method: slerp
base_model: Nitral-AI/Captain-Eris_Violet-V0.420-12B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.420
dtype: bfloat16
Downloads last month
7
Safetensors
Model size
12.2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for pot99rta/CaptainMaid-12B-VioletMell-V0.420