Modelpublic

RichardErkhov/jeiku_-_NarrativeNexus_7B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes148downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NarrativeNexus_7B - GGUF

—Model creator: https://huggingface.co/jeiku/
—Original model: https://huggingface.co/jeiku/NarrativeNexus_7B/

Name	Quant method	Size
NarrativeNexus_7B.Q2_K.gguf	Q2_K	2.53GB
NarrativeNexus_7B.IQ3_XS.gguf	IQ3_XS	2.81GB
NarrativeNexus_7B.IQ3_S.gguf	IQ3_S	2.96GB
NarrativeNexus_7B.Q3_K_S.gguf	Q3KS	2.95GB
NarrativeNexus_7B.IQ3_M.gguf	IQ3_M	3.06GB
NarrativeNexus_7B.Q3_K.gguf	Q3_K	3.28GB
NarrativeNexus_7B.Q3_K_M.gguf	Q3KM	3.28GB
NarrativeNexus_7B.Q3_K_L.gguf	Q3KL	3.56GB
NarrativeNexus_7B.IQ4_XS.gguf	IQ4_XS	3.67GB
NarrativeNexus_7B.Q4_0.gguf	Q4_0	3.83GB
NarrativeNexus_7B.IQ4_NL.gguf	IQ4_NL	3.87GB
NarrativeNexus_7B.Q4_K_S.gguf	Q4KS	3.86GB
NarrativeNexus_7B.Q4_K.gguf	Q4_K	4.07GB
NarrativeNexus_7B.Q4_K_M.gguf	Q4KM	4.07GB
NarrativeNexus_7B.Q4_1.gguf	Q4_1	4.24GB
NarrativeNexus_7B.Q5_0.gguf	Q5_0	4.65GB
NarrativeNexus_7B.Q5_K_S.gguf	Q5KS	4.65GB
NarrativeNexus_7B.Q5_K.gguf	Q5_K	4.78GB
NarrativeNexus_7B.Q5_K_M.gguf	Q5KM	4.78GB
NarrativeNexus_7B.Q5_1.gguf	Q5_1	5.07GB
NarrativeNexus_7B.Q6_K.gguf	Q6_K	5.53GB
NarrativeNexus_7B.Q8_0.gguf	Q8_0	7.17GB

Original model description: --- base_model:

—jeiku/Cookie_7B
—jeiku/SpaghettiOs_7B
—jeiku/Rainbow697B
—jeiku/ParanoidAndroid7B library_name: transformers tags:
—mergekit
—merge license: other ---

Nexus

This is my new favorite 7B, made from a merge of tunes and merges that I've tossed together over the last week or so. This model seems to be greater than the sum of its parts, and is performing well in riddle testing and markdown role playing. I have also been using this model to generate 1000 token narratives that I am using to improve custom story datasets for use with future models. It is highly descriptive and readily fills a futanari character. You can likely utilize it for female or male characters as well. Enjoy!

GGUF here: https://huggingface.co/jeiku/NarrativeNexus7BGGUF

image/jpeg

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 jeiku/Cookie_7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: dare_ties
base_model: jeiku/Cookie_7B
parameters:
  normalize: true
models:
  - model: jeiku/SpaghettiOs_7B
    parameters:
      weight: 1
  - model: jeiku/Rainbow_69_7B
    parameters:
      weight: 1
  - model: jeiku/Paranoid_Android_7B
    parameters:
      weight: 0.75            
dtype: float16