Quantization made by Richard Erkhov.

Evolutionstory - GGUF

Model creator: https://huggingface.co/ClaudioItaly/
Original model: https://huggingface.co/ClaudioItaly/Evolutionstory/

Name	Quant method	Size
Evolutionstory.Q2_K.gguf	Q2_K	2.53GB
Evolutionstory.IQ3_XS.gguf	IQ3_XS	2.81GB
Evolutionstory.IQ3_S.gguf	IQ3_S	2.96GB
Evolutionstory.Q3_K_S.gguf	Q3_K_S	2.95GB
Evolutionstory.IQ3_M.gguf	IQ3_M	3.06GB
Evolutionstory.Q3_K.gguf	Q3_K	3.28GB
Evolutionstory.Q3_K_M.gguf	Q3_K_M	3.28GB
Evolutionstory.Q3_K_L.gguf	Q3_K_L	3.56GB
Evolutionstory.IQ4_XS.gguf	IQ4_XS	3.67GB
Evolutionstory.Q4_0.gguf	Q4_0	3.83GB
Evolutionstory.IQ4_NL.gguf	IQ4_NL	3.87GB
Evolutionstory.Q4_K_S.gguf	Q4_K_S	3.86GB
Evolutionstory.Q4_K.gguf	Q4_K	4.07GB
Evolutionstory.Q4_K_M.gguf	Q4_K_M	4.07GB
Evolutionstory.Q4_1.gguf	Q4_1	4.24GB
Evolutionstory.Q5_0.gguf	Q5_0	4.65GB
Evolutionstory.Q5_K_S.gguf	Q5_K_S	4.65GB
Evolutionstory.Q5_K.gguf	Q5_K	4.78GB
Evolutionstory.Q5_K_M.gguf	Q5_K_M	4.78GB
Evolutionstory.Q5_1.gguf	Q5_1	5.07GB
Evolutionstory.Q6_K.gguf	Q6_K	5.53GB
Evolutionstory.Q8_0.gguf	Q8_0	7.17GB

Original model description:

base_model:

mergekit-community/TopEvolution
ClaudioItaly/Evolutionstory
lucyknada/microsoft_WizardLM-2-7B 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 mergekit-community/TopEvolution 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: ClaudioItaly/Evolutionstory
    parameters:
      density: 0.5
      weight: 0.5
  - model: lucyknada/microsoft_WizardLM-2-7B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: mergekit-community/TopEvolution
parameters:
  normalize: false
  int8_mask: true
dtype: float16