Quantization made by Richard Erkhov.

TARS-8B - GGUF

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

Name	Quant method	Size
TARS-8B.Q2_K.gguf	Q2_K	2.96GB
TARS-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
TARS-8B.IQ3_S.gguf	IQ3_S	3.43GB
TARS-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
TARS-8B.IQ3_M.gguf	IQ3_M	3.52GB
TARS-8B.Q3_K.gguf	Q3_K	3.74GB
TARS-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
TARS-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
TARS-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
TARS-8B.Q4_0.gguf	Q4_0	4.34GB
TARS-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
TARS-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
TARS-8B.Q4_K.gguf	Q4_K	4.58GB
TARS-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
TARS-8B.Q4_1.gguf	Q4_1	4.78GB
TARS-8B.Q5_0.gguf	Q5_0	5.21GB
TARS-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
TARS-8B.Q5_K.gguf	Q5_K	5.34GB
TARS-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
TARS-8B.Q5_1.gguf	Q5_1	5.65GB
TARS-8B.Q6_K.gguf	Q6_K	6.14GB
TARS-8B.Q8_0.gguf	Q8_0	7.95GB

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:

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