wraithorn

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

Merge Details

Merge Method

This model was merged using the DELLA merge method using kromcomp/L3.1-Adumbralv1-12B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: kromcomp/L3.1-Adumbralv1-12B
chat_template: llama3
dtype: float32
merge_method: della
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 50]
        model: kromcomp/L3.1-Roseatev2-12B
        parameters:
          density: 0.35
          epsilon: 0.15
          lambda: 1.0
          weight: [0.2, 0.3, 0.5]
      - layer_range: [0, 50]
        model: kromcomp/L3.1-Vexationv1-12B
        parameters:
          density: 0.3
          epsilon: 0.1
          lambda: 1.0
          weight: [0.15, 0.3, 0.2]
      - layer_range: [0, 50]
        model: kromcomp/L3.1-Adumbralv1-12B
        parameters:
          density: 0.5
          epsilon: 0.1
          lambda: 1.0
          weight: [0.65, 0.4, 0.3]
parameters:
  int8_mask: 1.0
  normalize: 0.0
tokenizer:
  pad_to_multiple_of: 32
Downloads last month
3
Safetensors
Model size
12B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for kromcomp/L3.1-Wraithornv6-12B