Modelpublic

RichardErkhov/mergekit-community_-_nerp_slerp_nsfw-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes726downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

nerpslerpnsfw - GGUF

—Model creator: https://huggingface.co/mergekit-community/
—Original model: https://huggingface.co/mergekit-community/nerpslerpnsfw/

Name	Quant method	Size
nerp_slerp_nsfw.Q2_K.gguf	Q2_K	2.96GB
nerp_slerp_nsfw.IQ3_XS.gguf	IQ3_XS	3.28GB
nerp_slerp_nsfw.IQ3_S.gguf	IQ3_S	3.43GB
nerp_slerp_nsfw.Q3_K_S.gguf	Q3KS	3.41GB
nerp_slerp_nsfw.IQ3_M.gguf	IQ3_M	3.52GB
nerp_slerp_nsfw.Q3_K.gguf	Q3_K	3.74GB
nerp_slerp_nsfw.Q3_K_M.gguf	Q3KM	3.74GB
nerp_slerp_nsfw.Q3_K_L.gguf	Q3KL	4.03GB
nerp_slerp_nsfw.IQ4_XS.gguf	IQ4_XS	4.18GB
nerp_slerp_nsfw.Q4_0.gguf	Q4_0	4.34GB
nerp_slerp_nsfw.IQ4_NL.gguf	IQ4_NL	4.38GB
nerp_slerp_nsfw.Q4_K_S.gguf	Q4KS	4.37GB
nerp_slerp_nsfw.Q4_K.gguf	Q4_K	4.58GB
nerp_slerp_nsfw.Q4_K_M.gguf	Q4KM	4.58GB
nerp_slerp_nsfw.Q4_1.gguf	Q4_1	4.78GB
nerp_slerp_nsfw.Q5_0.gguf	Q5_0	5.21GB
nerp_slerp_nsfw.Q5_K_S.gguf	Q5KS	5.21GB
nerp_slerp_nsfw.Q5_K.gguf	Q5_K	5.34GB
nerp_slerp_nsfw.Q5_K_M.gguf	Q5KM	5.34GB
nerp_slerp_nsfw.Q5_1.gguf	Q5_1	5.65GB
nerp_slerp_nsfw.Q6_K.gguf	Q6_K	6.14GB
nerp_slerp_nsfw.Q8_0.gguf	Q8_0	7.95GB

Original model description: --- base_model:

—DreadPoor/HappyNewYear-8B-Model_Stock
—mergekit-community/mergekit-modelstock-fpfjlqs libraryname: 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:

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
      - model: DreadPoor/Happy_New_Year-8B-Model_Stock
        layer_range: [0, 32]
      - model: mergekit-community/mergekit-model_stock-fpfjlqs
        layer_range: [0, 32]
merge_method: slerp
base_model: DreadPoor/Happy_New_Year-8B-Model_Stock
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16