metadata

base_model:
  - mergekit-community/L3-Boshima-a
  - kromeurus/L3.1-Aglow-Vulca-v0.1-8B
  - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
  - Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
  - failspy/Llama-3-8B-Instruct-MopeyMule
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 Model Stock merge method using ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
tokenizer_source: base
base_model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
models:
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
    parameters:
      weight: 0.8
  - model: mergekit-community/L3-Boshima-a
    parameters:
      weight: 0.8
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
    parameters:
      weight: 0.8
  - model: kromeurus/L3.1-Aglow-Vulca-v0.1-8B
    parameters:
      weight: 0.6
  - model: failspy/Llama-3-8B-Instruct-MopeyMule
    parameters:
      weight: 0.4
parameters:
  normalize: true