metadata

base_model: Locutusque/Llama-3-Yggdrasil-8B
inference: true
library_name: transformers
license: llama3
model_creator: Locutusque
model_name: Llama-3-Yggdrasil-8B
pipeline_tag: text-generation
quantized_by: afrideva
tags:
  - mergekit
  - merge
  - gguf
  - ggml
  - quantized

Llama-3-Yggdrasil-8B-GGUF

Quantized GGUF model files for Llama-3-Yggdrasil-8B from Locutusque

Original Model Card:

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using NousResearch/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Meta-Llama-3-8B
    # No parameters necessary for base model
  - model: NousResearch/Meta-Llama-3-8B-Instruct
    parameters:
      density: 0.6
      weight: 0.55
  - model: Locutusque/llama-3-neural-chat-v2.2-8b
    parameters:
      density: 0.55
      weight: 0.45
  - model: Locutusque/Llama-3-Hercules-5.0-8B
    parameters:
      density: 0.57
      weight: 0.5
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
parameters:
  int8_mask: true
dtype: bfloat16