L3.1-Subfuscv1-12B / README.md
kromeurus's picture
Upload folder using huggingface_hub
02d6306 verified
metadata
base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

subfusc

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:

  • merge/daspel

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 8]
    model: merge/daspel
- sources:
  - layer_range: [4, 8]
    model: merge/daspel
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [8, 12]
    model: merge/daspel
- sources:
  - layer_range: [8, 12]
    model: merge/daspel
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [12, 16]
    model: merge/daspel
- sources:
  - layer_range: [12, 16]
    model: merge/daspel
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [16, 28]
    model: merge/daspel
- sources:
  - layer_range: [24, 28]
    model: merge/daspel
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [28, 32]
    model: merge/daspel
- sources:
  - layer_range: [30, 32]
    model: merge/daspel
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0