Quantization made by Richard Erkhov.

mergekit-ties-xvxbphx - GGUF

Model creator: https://huggingface.co/llm-wizard/
Original model: https://huggingface.co/llm-wizard/mergekit-ties-xvxbphx/

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

Original model description:

base_model:

ai-maker-space/leagaleasy-llama-3-instruct-v2
ai-maker-space/riddle-bot-v1
NousResearch/Meta-Llama-3-8B-Instruct library_name: transformers tags:
mergekit
merge

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 NousResearch/Meta-Llama-3-8B-Instruct 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-Instruct
  - model: ai-maker-space/leagaleasy-llama-3-instruct-v2
    parameters:
      density: 0.5
      weight: 0.5
  - model: ai-maker-space/riddle-bot-v1
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: NousResearch/Meta-Llama-3-8B-Instruct
parameters:
  normalize: false
  int8_mask: true
dtype: float16