README.md

metadata

base_model:
  - smelborp/MixtralOrochi8x7B
library_name: transformers
tags:
  - mergekit
  - merge

maid-yuzu-v8

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

v7's approach worked better than I thought, so I tried something even weirder as a test. I don't think a proper model will come out, but I'm curious about the results.

Merge Details

Merge Method

This models were merged using the SLERP method in the following order:

maid-yuzu-v8-base: mistralai/Mixtral-8x7B-v0.1 + mistralai/Mixtral-8x7B-Instruct-v0.1 = 0.5
maid-yuzu-v8-step1: above + jondurbin/bagel-dpo-8x7b-v0.2 = 0.25
maid-yuzu-v8-step2: above + cognitivecomputations/dolphin-2.7-mixtral-8x7b = 0.25
maid-yuzu-v8-step3: above + NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss = 0.25
maid-yuzu-v8-step4: above + ycros/BagelMIsteryTour-v2-8x7B = 0.25
maid-yuzu-v8: above + smelborp/MixtralOrochi8x7B = 0.25

Models Merged

The following models were included in the merge:

• smelborp/MixtralOrochi8x7B
• ../maid-yuzu-v8-step4

Configuration

The following YAML configuration was used to produce this model:

base_model:
  model:
    path: ../maid-yuzu-v8-step4
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - value: 0.25
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: ../maid-yuzu-v8-step4
  - layer_range: [0, 32]
    model:
      model:
        path: smelborp/MixtralOrochi8x7B