README.md

metadata

base_model:
  - anthracite-org/magnum-v2.5-12b-kto
  - nbeerbower/mistral-nemo-wissenschaft-12B
  - EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Ollama template

TEMPLATE """{{ if .System }}[INST]system
{{ .System }}[\INST]
{{ end }}{{ if .Prompt }}[INST]user
{{ .Prompt }}[\INST]
{{ end }}[INST]assistant
{{ .Response }}[\INST]</s>
"""
PARAMETER stop "</s>"
PARAMETER stop "[\INST]"

Merge Details

Merge Method

This model was merged using the TIES merge method using anthracite-org/magnum-v2.5-12b-kto as a base.

Models Merged

The following models were included in the merge:

• nbeerbower/mistral-nemo-wissenschaft-12B
• EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: anthracite-org/magnum-v2.5-12b-kto
    #no parameters necessary for base model
  - model: EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math
    parameters:
      density: 0.5
      weight: 0.5
  - model: nbeerbower/mistral-nemo-wissenschaft-12B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: anthracite-org/magnum-v2.5-12b-kto
parameters:
  normalize: false
  int8_mask: true
dtype: float16