README.md

metadata

base_model:
  - georgesung/llama2_7b_chat_uncensored
  - NousResearch/Llama-2-7b-chat-hf
library_name: transformers
tags:
  - mergekit
  - merge

LlamaKinda

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 NousResearch/Llama-2-7b-chat-hf as a base.

Models Merged

The following models were included in the merge:

• georgesung/llama2_7b_chat_uncensored

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: georgesung/llama2_7b_chat_uncensored
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: NousResearch/Llama-2-7b-chat-hf
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
merge_method: ties
base_model: NousResearch/Llama-2-7b-chat-hf
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16