RichardErkhov/picAIso_-_TARS-8B-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TARS-8B - bnb 4bits

• Model creator: https://huggingface.co/picAIso/
• Original model: https://huggingface.co/picAIso/TARS-8B/

Original model description:

base_model: - NousResearch/Hermes-2-Pro-Llama-3-8B - nbeerbower/llama-3-gutenberg-8B - MaziyarPanahi/Llama-3-8B-Instruct-v0.9 library_name: transformers tags: - mergekit - merge - merging - llama3 - merged license: llama3 language: - en

merge

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 MaziyarPanahi/Llama-3-8B-Instruct-v0.9 as a base.

Models Merged

The following models were included in the merge:

• NousResearch/Hermes-2-Pro-Llama-3-8B
• nbeerbower/llama-3-gutenberg-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9
    #no parameters necessary for base model
  - model: NousResearch/Hermes-2-Pro-Llama-3-8B
    parameters:
      density: 0.5
      weight: 0.8
  - model: nbeerbower/llama-3-gutenberg-8B
    parameters:
      density: 0.5
      weight: 0.8

merge_method: ties
base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9
parameters:
  normalize: false
  int8_mask: true
dtype: float16