README.md

metadata

base_model:
  - rityak/L3.1-HermesBreakGradient-8B
  - rityak/L3.1-DarkStock-8B
library_name: transformers
tags:
  - mergekit
  - merge

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:

• rityak/L3.1-HermesBreakGradient-8B
• rityak/L3.1-DarkStock-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: rityak/L3.1-HermesBreakGradient-8B
        layer_range: [0, 8]
  - sources:
      - model: rityak/L3.1-DarkStock-8B
        layer_range: [4, 12]
  - sources:
      - model: rityak/L3.1-HermesBreakGradient-8B
        layer_range: [9, 16]
  - sources:
      - model: rityak/L3.1-DarkStock-8B
        layer_range: [13, 20]
  - sources:
      - model: rityak/L3.1-HermesBreakGradient-8B
        layer_range: [17, 24]
  - sources:
      - model: rityak/L3.1-DarkStock-8B
        layer_range: [21, 28]
  - sources:
      - model: rityak/L3.1-HermesBreakGradient-8B
        layer_range: [25, 32]
merge_method: passthrough
dtype: bfloat16
parameters:
  normalize: false
  int8_mask: true