README.md

metadata

base_model:
  - Nexusflow/Starling-LM-7B-beta
  - ABX-AI/Infinite-Laymons-7B
library_name: transformers
tags:
  - mergekit
  - merge
  - mistral
  - not-for-all-audiences

Starfinite-Laymons-7B

A mid-step merge that I did in order to create ABX-AI/Starbral-Infinimons-9B

It is more prone to alignment, however feel free to test it or request GGUF if you like it.

Merge Details

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

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• Nexusflow/Starling-LM-7B-beta
• ABX-AI/Infinite-Laymons-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Nexusflow/Starling-LM-7B-beta
        layer_range: [0, 32]
      - model: ABX-AI/Infinite-Laymons-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: ABX-AI/Infinite-Laymons-7B
parameters:
  t:
    - filter: self_attn
      value: [0.7, 0.3, 0.6, 0.2, 0.5]
    - filter: mlp
      value: [0.3, 0.7, 0.4, 0.8, 0.5]
    - value: 0.5
dtype: bfloat16