README.md

metadata

base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

out

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

Merge Details

Merge Method

This model was merged using the TIES merge method using /mnt/ue/fp16-2/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated as a base.

Models Merged

The following models were included in the merge:

• /mnt/bigly/fp16/Llama3-PBM-Nova-70B
• /mnt/bigly/fp16/Llama-3-Taiwan-70B-Instruct
• /mnt/ue/fp16-2/BaseModelsMerged
• /mnt/ue/fp16-2/L3.3-70B-Euryale-v2.3

Configuration

The following YAML configuration was used to produce this model:

merge_method: ties
base_model: /mnt/ue/fp16-2/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
models:
  - model: /mnt/bigly/fp16/Llama3-PBM-Nova-70B
    parameters:
      weight: 1.0
      density: 0.7
  - model: /mnt/bigly/fp16/Llama-3-Taiwan-70B-Instruct
    parameters:
      weight: 1.0
      density: 0.7
  - model: /mnt/ue/fp16-2/L3.3-70B-Euryale-v2.3
    parameters:
      weight: 1.0
      density: 0.7
  - model: /mnt/ue/fp16-2/BaseModelsMerged
    parameters:
      weight: 1.0
      density: 0.7
dtype: float16