Quantization made by Richard Erkhov.

Github

Discord

Request more models

Evolved-Llama3-ELYZA-Uncensored-8B - GGUF

• Model creator: https://huggingface.co/kinakomochi/
• Original model: https://huggingface.co/kinakomochi/Evolved-Llama3-ELYZA-Uncensored-8B/

Original model description:

base_model: []
library_name: transformers
tags:

• mergekit
• merge
  language:
• ja

merge

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using Llama-3-ELYZA-JP-8B as a base.

Models Merged

The following models were included in the merge:

• LLama-3-8b-Uncensored

Configuration

The following YAML configuration was used to produce this model:

base_model: Llama-3-ELYZA-JP-8B_2371007997
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 8]
    model: Llama-3-ELYZA-JP-8B_2371007997
    parameters:
      weight: 0.6009853792520561
  - layer_range: [0, 8]
    model: LLama-3-8b-Uncensored_3533367681
    parameters:
      weight: 0.6426472022803525
- sources:
  - layer_range: [8, 16]
    model: Llama-3-ELYZA-JP-8B_2371007997
    parameters:
      weight: 0.9637092777121993
  - layer_range: [8, 16]
    model: LLama-3-8b-Uncensored_3533367681
    parameters:
      weight: 0.04643386869454866
- sources:
  - layer_range: [16, 24]
    model: Llama-3-ELYZA-JP-8B_2371007997
    parameters:
      weight: 0.8126375881596057
  - layer_range: [16, 24]
    model: LLama-3-8b-Uncensored_3533367681
    parameters:
      weight: -0.09409093863958298
- sources:
  - layer_range: [24, 32]
    model: Llama-3-ELYZA-JP-8B_2371007997
    parameters:
      weight: 1.0678042108768628
  - layer_range: [24, 32]
    model: LLama-3-8b-Uncensored_3533367681
    parameters:
      weight: -0.29934185707062755