Pretergeek's picture
Update README.md
1a31216 verified
|
raw
history blame
No virus
5.76 kB
metadata
base_model:
  - openchat/openchat-3.5-0106
library_name: transformers
tags:
  - mergekit
  - merge
license: apache-2.0

Untitled Model (1)

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: openchat/openchat-3.5-0106
      layer_range: [0, 2]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [1, 2]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [2, 4]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [3, 4]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [4, 6]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [5, 6]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [6, 8]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [7, 8]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [8, 10]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [9, 10]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [10, 12]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [11, 12]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [12, 14]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [13, 14]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [14, 16]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [15, 16]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [16, 18]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [17, 18]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [18, 20]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [19, 20]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [20, 22]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [21, 22]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [22, 24]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [23, 24]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [24, 26]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [25, 26]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [26, 28]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [27, 28]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [28, 30]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [29, 30]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [30, 32]
  - sources:
    - model: openchat/openchat-3.5-0106
      layer_range: [31, 32]
      parameters:
        scale:
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
merge_method: passthrough
dtype: bfloat16