metadata

base_model:
  - NaniDAO/Llama-3.3-70B-Instruct-ablated
  - huihui-ai/Llama-3.3-70B-Instruct-abliterated
  - nbeerbower/Llama-3.1-Nemotron-lorablated-70B
  - SentientAGI/Dobby-Unhinged-Llama-3.3-70B
  - SicariusSicariiStuff/Negative_LLAMA_70B
library_name: transformers
tags:
  - mergekit
  - merge
license: llama3.3

Cornerstone-0.1-LLaMA-70B

This experimental merged model combines several abliterated models and Negative_LLAMA_70B to create a less biased and uncensored foundation, serving as a base for subsequent merges.

I forgot to convert the model to bf16. It will be corrected in the next version.

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

Merge Details

Merge Method

This model was merged using the SCE merge method using huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
merge_method: sce
dtype: float32
models:
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
  - model: NaniDAO/Llama-3.3-70B-Instruct-ablated
  - model: SentientAGI/Dobby-Unhinged-Llama-3.3-70B
  - model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B