README.md

metadata

base_model:
  - alpindale/WizardLM-2-8x22B
  - mistralai/Mixtral-8x22B-Instruct-v0.1
tags:
  - mergekit
  - merge
license: apache-2.0

Probably BROKEN, look for v0.2 which should be working!

• Test merge of two extremely large MoE models using SLERP. Don't know if it's working yet, haven't had time or hardware to test.

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:

• alpindale/WizardLM-2-8x22B
• mistralai/Mixtral-8x22B-Instruct-v0.1

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: mistralai/Mixtral-8x22B-Instruct-v0.1
        layer_range: [0, 55]
      - model: alpindale/WizardLM-2-8x22B
        layer_range: [0, 55]
merge_method: slerp
base_model: mistralai/Mixtral-8x22B-Instruct-v0.1
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: 0.5
dtype: bfloat16