Modelpublic

RichardErkhov/jeiku_-_mergefodder2-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes149downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergefodder2 - GGUF

—Model creator: https://huggingface.co/jeiku/
—Original model: https://huggingface.co/jeiku/mergefodder2/

Name	Quant method	Size
mergefodder2.Q2_K.gguf	Q2_K	1.71GB
mergefodder2.IQ3_XS.gguf	IQ3_XS	1.89GB
mergefodder2.IQ3_S.gguf	IQ3_S	1.97GB
mergefodder2.Q3_K_S.gguf	Q3KS	1.96GB
mergefodder2.IQ3_M.gguf	IQ3_M	2.03GB
mergefodder2.Q3_K.gguf	Q3_K	2.14GB
mergefodder2.Q3_K_M.gguf	Q3KM	2.14GB
mergefodder2.Q3_K_L.gguf	Q3KL	2.3GB
mergefodder2.IQ4_XS.gguf	IQ4_XS	2.38GB
mergefodder2.Q4_0.gguf	Q4_0	2.47GB
mergefodder2.IQ4_NL.gguf	IQ4_NL	2.49GB
mergefodder2.Q4_K_S.gguf	Q4KS	2.48GB
mergefodder2.Q4_K.gguf	Q4_K	2.59GB
mergefodder2.Q4_K_M.gguf	Q4KM	2.59GB
mergefodder2.Q4_1.gguf	Q4_1	2.71GB
mergefodder2.Q5_0.gguf	Q5_0	2.95GB
mergefodder2.Q5_K_S.gguf	Q5KS	2.95GB
mergefodder2.Q5_K.gguf	Q5_K	3.01GB
mergefodder2.Q5_K_M.gguf	Q5KM	3.01GB
mergefodder2.Q5_1.gguf	Q5_1	3.19GB
mergefodder2.Q6_K.gguf	Q6_K	3.46GB
mergefodder2.Q8_0.gguf	Q8_0	4.47GB

Original model description: --- base_model:

—jeiku/nuggiespoe
—jeiku/zenithquantum 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 SLERP merge method.

Models Merged

The following models were included in the merge:

—jeiku/nuggiespoe
—jeiku/zenithquantum

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: jeiku/zenithquantum
  - model: jeiku/nuggiespoe
merge_method: slerp
base_model: jeiku/nuggiespoe
parameters:
  t:
   - value: 0.5
dtype: bfloat16